Daily Papers

Large language models (LLMs) power a new generation of interactive AI applications exemplified by ChatGPT. The interactive nature of these applications demand low job completion time (JCT) for model inference. Existing LLM serving systems use run-to-completion processing for inference jobs, which suffers from head-of-line blocking and long JCT. We present FastServe, a distributed inference serving system for LLMs. FastServe exploits the autoregressive pattern of LLM inference to enable preemption at the granularity of each output token. FastServe uses preemptive scheduling to minimize JCT with a novel skip-join Multi-Level Feedback Queue scheduler. Based on the new semi information-agnostic setting of LLM inference, the scheduler leverages the input length information to assign an appropriate initial queue for each arrival job to join. The higher priority queues than the joined queue are skipped to reduce demotions. We design an efficient GPU memory management mechanism that proactively offloads and uploads intermediate states between GPU memory and host memory for LLM inference. We build a system prototype of FastServe based on NVIDIA FasterTransformer. Experimental results show that compared to the state-of-the-art solution Orca, FastServe improves the average and tail JCT by up to 5.1times and 6.4times, respectively.

The reasoning large language model (RLLM) has been proven competitive in solving complex reasoning tasks such as mathematics, coding, compared to general LLM. However, the serving performance and behavior of RLLM remains unexplored, which may undermine the deployment and utilization of RLLM in real-world scenario. To close this gap, in this paper, we conduct a comprehensive study of RLLM service. We first perform a pilot study on comparing the serving performance between RLLM and traditional LLM and reveal that there are several distinct differences regarding serving behavior: (1) significant memory usage and fluctuations; (2) straggler requests; (3) adaptive running time; (4) domain preference. Then we further investigate whether existing inference optimization techniques are valid for RLLM. Our main takeaways are that model quantization methods and speculative decoding can improve service system efficiency with small compromise to RLLM accuracy, while prefix caching, KV cache quantization may even degrade accuracy or serving performance for small RLLM. Lastly, we conduct evaluation under real world workload modeled by Gamma distribution to verify our findings. Empirical results of real world workload evaluation across different dataset are aligned with our main findings regarding RLLM serving. We hope our work can provide the research community and industry with insights to advance RLLM inference serving.

Large Language Models (LLMs) are revolutionizing numerous industries, but their substantial computational demands create challenges for efficient deployment, particularly in cloud environments. Traditional approaches to inference serving often struggle with resource inefficiencies, leading to high operational costs, latency issues, and limited scalability. This article explores how Cloud Native technologies, such as containerization, microservices, and dynamic scheduling, can fundamentally improve LLM inference serving. By leveraging these technologies, we demonstrate how a Cloud Native system enables more efficient resource allocation, reduces latency, and enhances throughput in high-demand scenarios. Through real-world evaluations using Kubernetes-based autoscaling, we show that Cloud Native architectures can dynamically adapt to workload fluctuations, mitigating performance bottlenecks while optimizing LLM inference serving performance. This discussion provides a broader perspective on how Cloud Native frameworks could reshape the future of scalable LLM inference serving, offering key insights for researchers, practitioners, and industry leaders in cloud computing and artificial intelligence.

Speculative inference is a promising paradigm employing small speculative models (SSMs) as drafters to generate draft tokens, which are subsequently verified in parallel by the target large language model (LLM). This approach enhances the efficiency of inference serving by reducing LLM inference latency and costs while preserving generation quality. However, existing speculative methods face critical challenges, including inefficient resource utilization and limited draft acceptance, which constrain their scalability and overall effectiveness. To overcome these obstacles, we present CoSine, a novel speculative inference system that decouples sequential speculative decoding from parallel verification, enabling efficient collaboration among multiple nodes. Specifically, CoSine routes inference requests to specialized drafters based on their expertise and incorporates a confidence-based token fusion mechanism to synthesize outputs from cooperating drafters, ensuring high-quality draft generation. Additionally, CoSine dynamically orchestrates the execution of speculative decoding and verification in a pipelined manner, employing batch scheduling to selectively group requests and adaptive speculation control to minimize idle periods. By optimizing parallel workflows through heterogeneous node collaboration, CoSine balances draft generation and verification throughput in real-time, thereby maximizing resource utilization. Experimental results demonstrate that CoSine achieves superior performance compared to state-of-the-art speculative approaches. Notably, with equivalent resource costs, CoSine achieves up to a 23.2% decrease in latency and a 32.5% increase in throughput compared to baseline methods.

Modern applications increasingly rely on inference serving systems to provide low-latency insights with a diverse set of machine learning models. Existing systems often utilize resource elasticity to scale with demand. However, many applications cannot rely on hardware scaling when deployed at the edge or other resource-constrained environments. In this work, we propose a model selection and scheduling algorithm that implements accuracy scaling to increase efficiency for these more constrained deployments. We show that existing schedulers that make decisions using profiled model accuracy are biased toward the label distribution present in the test dataset. To address this problem, we propose using ML models -- which we call SneakPeek models -- to dynamically adjust estimates of model accuracy, based on the underlying data. Furthermore, we greedily incorporate inference batching into scheduling decisions to improve throughput and avoid the overhead of swapping models in and out of GPU memory. Our approach employs a new notion of request priority, which navigates the trade-off between attaining high accuracy and satisfying deadlines. Using data and models from three real-world applications, we show that our proposed approaches result in higher-utility schedules and higher accuracy inferences in these hardware-constrained environments.

In the context of Machine Learning as a Service (MLaaS) clouds, the extensive use of Large Language Models (LLMs) often requires efficient management of significant query loads. When providing real-time inference services, several challenges arise. Firstly, increasing the number of GPUs may lead to a decrease in inference speed due to heightened communication overhead, while an inadequate number of GPUs can lead to out-of-memory errors. Secondly, different deployment strategies need to be evaluated to guarantee optimal utilization and minimal inference latency. Lastly, inefficient orchestration of inference queries can easily lead to significant Service Level Objective (SLO) violations. Lastly, inefficient orchestration of inference queries can easily lead to significant Service Level Objective (SLO) violations. To address these challenges, we propose a Unified and Efficient approach for Large Language Model inference serving (UELLM), which consists of three main components: 1) resource profiler, 2) batch scheduler, and 3) LLM deployer. UELLM minimizes resource overhead, reduces inference latency, and lowers SLO violation rates. Compared with state-of-the-art (SOTA) techniques, UELLM reduces the inference latency by 72.3% to 90.3%, enhances GPU utilization by 1.2X to 4.1X, and increases throughput by 1.92X to 4.98X, it can also serve without violating the inference latency SLO.

Transformers, driven by attention mechanisms, form the foundation of large language models (LLMs). As these models scale up, efficient GPU attention kernels become essential for high-throughput and low-latency inference. Diverse LLM applications demand flexible and high-performance attention solutions. We present FlashInfer: a customizable and efficient attention engine for LLM serving. FlashInfer tackles KV-cache storage heterogeneity using block-sparse format and composable formats to optimize memory access and reduce redundancy. It also offers a customizable attention template, enabling adaptation to various settings through Just-In-Time (JIT) compilation. Additionally, FlashInfer's load-balanced scheduling algorithm adjusts to dynamism of user requests while maintaining compatibility with CUDAGraph which requires static configuration. FlashInfer have been integrated into leading LLM serving frameworks like SGLang, vLLM and MLC-Engine. Comprehensive kernel-level and end-to-end evaluations demonstrate FlashInfer's ability to significantly boost kernel performance across diverse inference scenarios: compared to state-of-the-art LLM serving solutions, FlashInfer achieve 29-69% inter-token-latency reduction compared to compiler backends for LLM serving benchmark, 28-30% latency reduction for long-context inference, and 13-17% speedup for LLM serving with parallel generation.

Large Language Models (LLMs) for Generative AI have achieved remarkable progress, evolving into sophisticated and versatile tools widely adopted across various domains and applications. However, the substantial memory overhead caused by their vast number of parameters, combined with the high computational demands of the attention mechanism, poses significant challenges in achieving low latency and high throughput for LLM inference services. Recent advancements, driven by groundbreaking research, have significantly accelerated progress in this field. This paper provides a comprehensive survey of these methods, covering fundamental instance-level approaches, in-depth cluster-level strategies, emerging scenario directions, and other miscellaneous but important areas. At the instance level, we review model placement, request scheduling, decoding length prediction, storage management, and the disaggregation paradigm. At the cluster level, we explore GPU cluster deployment, multi-instance load balancing, and cloud service solutions. For emerging scenarios, we organize the discussion around specific tasks, modules, and auxiliary methods. To ensure a holistic overview, we also highlight several niche yet critical areas. Finally, we outline potential research directions to further advance the field of LLM inference serving.

Inference serving for large language models (LLMs) is the key to unleashing their potential in people's daily lives. However, efficient LLM serving remains challenging today because the requests are inherently heterogeneous and unpredictable in terms of resource and latency requirements, as a result of the diverse applications and the dynamic execution nature of LLMs. Existing systems are fundamentally limited in handling these characteristics and cause problems such as severe queuing delays, poor tail latencies, and SLO violations. We introduce Llumnix, an LLM serving system that reacts to such heterogeneous and unpredictable requests by runtime rescheduling across multiple model instances. Similar to context switching across CPU cores in modern operating systems, Llumnix reschedules requests to improve load balancing and isolation, mitigate resource fragmentation, and differentiate request priorities and SLOs. Llumnix implements the rescheduling with an efficient and scalable live migration mechanism for requests and their in-memory states, and exploits it in a dynamic scheduling policy that unifies the multiple rescheduling scenarios elegantly. Our evaluations show that Llumnix improves tail latencies by an order of magnitude, accelerates high-priority requests by up to 1.5x, and delivers up to 36% cost savings while achieving similar tail latencies, compared against state-of-the-art LLM serving systems. Llumnix is publicly available at https://github.com/AlibabaPAI/llumnix.

Transformer-based large language model (LLM) inference serving is now the backbone of many cloud services. LLM inference consists of a prefill phase and a decode phase. However, existing LLM deployment practices often overlook the distinct characteristics of these phases, leading to significant interference. To mitigate interference, our insight is to carefully schedule and group inference requests based on their characteristics. We realize this idea in TetriInfer through three pillars. First, it partitions prompts into fixed-size chunks so that the accelerator always runs close to its computationsaturated limit. Second, it disaggregates prefill and decode instances so each can run independently. Finally, it uses a smart two-level scheduling algorithm augmented with predicted resource usage to avoid decode scheduling hotspots. Results show that TetriInfer improves time-to-first-token (TTFT), job completion time (JCT), and inference efficiency in turns of performance per dollar by a large margin, e.g., it uses 38% less resources all the while lowering average TTFT and average JCT by 97% and 47%, respectively.

LLM inference for popular enterprise use cases, such as summarization, RAG, and code-generation, typically observes orders of magnitude longer prompt lengths than generation lengths. This characteristic leads to high cost of prefill and increased response latency. In this paper, we present SwiftKV, a novel model transformation and distillation procedure specifically designed to reduce the time and cost of processing prompt tokens while preserving high quality of generated tokens. SwiftKV combines three key mechanisms: i) SingleInputKV, which prefills later layers' KV cache using a much earlier layer's output, allowing prompt tokens to skip much of the model computation, ii) AcrossKV, which merges the KV caches of neighboring layers to reduce the memory footprint and support larger batch size for higher throughput, and iii) a knowledge-preserving distillation procedure that can adapt existing LLMs for SwiftKV with minimal accuracy impact and low compute and data requirement. For Llama-3.1-8B and 70B, SwiftKV reduces the compute requirement of prefill by 50% and the memory requirement of the KV cache by 62.5% while incurring minimum quality degradation across a wide range of tasks. In the end-to-end inference serving using an optimized vLLM implementation, SwiftKV realizes up to 2x higher aggregate throughput and 60% lower time per output token. It can achieve a staggering 560 TFlops/GPU of normalized inference throughput, which translates to 16K tokens/s for Llama-3.1-70B in 16-bit precision on 4x H100 GPUs.

Large Language Models (LLMs) represent a revolutionary advancement in the contemporary landscape of artificial general intelligence (AGI). As exemplified by ChatGPT, LLM-based applications necessitate minimal response latency and maximal throughput for inference serving. However, due to the unpredictability of LLM execution, the first-come-first-serve (FCFS) scheduling policy employed by current LLM serving systems suffers from head-of-line (HoL) blocking issues and long job response times. In this paper, we propose a new efficient LLM inference serving framework, named ALISE. The key design paradigm of ALISE is to leverage a novel speculative scheduler by estimating the execution time for each job and exploiting such prior knowledge to assign appropriate job priority orders, thus minimizing potential queuing delays for heterogeneous workloads. Furthermore, to mitigate the memory overhead of the intermediate key-value (KV) cache, we employ a priority-based adaptive memory management protocol and quantization-based compression techniques. Evaluations demonstrate that in comparison to the state-of-the-art solution vLLM, ALISE improves the throughput of inference serving by up to 1.8x and 2.1x under the same latency constraint on the Alpaca and ShareGPT datasets, respectively.

With the ubiquitous use of modern large language models (LLMs) across industries, the inference serving for these models is ever expanding. Given the high compute and memory requirements of modern LLMs, more and more top-of-the-line GPUs are being deployed to serve these models. Energy availability has come to the forefront as the biggest challenge for data center expansion to serve these models. In this paper, we present the trade-offs brought up by making energy efficiency the primary goal of LLM serving under performance SLOs. We show that depending on the inputs, the model, and the service-level agreements, there are several knobs available to the LLM inference provider to use for being energy efficient. We characterize the impact of these knobs on the latency, throughput, as well as the energy. By exploring these trade-offs, we offer valuable insights into optimizing energy usage without compromising on performance, thereby paving the way for sustainable and cost-effective LLM deployment in data center environments.

With the widespread adoption of Large Language Models (LLMs), serving LLM inference requests has become an increasingly important task, attracting active research advancements. Practical workloads play an essential role in this process: they are critical for motivating and benchmarking serving techniques and systems. However, the existing understanding of real-world LLM serving workloads is limited due to the lack of a comprehensive workload characterization. Prior analyses remain insufficient in scale and scope, thus failing to fully capture intricate workload characteristics. In this paper, we fill the gap with an in-depth characterization of LLM serving workloads collected from our worldwide cloud inference serving service, covering not only language models but also emerging multimodal and reasoning models, and unveiling important new findings in each case. Moreover, based on our findings, we propose ServeGen, a principled framework for generating realistic LLM serving workloads by composing them on a per-client basis. A practical use case in production validates that ServeGen avoids 50% under-provisioning compared to naive workload generation, demonstrating ServeGen's advantage in performance benchmarking. We will open-source ServeGen to foster future research.

Two widely adopted techniques for LLM inference serving systems today are hybrid batching and disaggregated serving. A hybrid batch combines prefill and decode tokens of different requests in the same batch to improve resource utilization and throughput at the cost of increased latency per token. In contrast, disaggregated serving decouples compute-bound prefill and bandwidth-bound decode phases to optimize for service level objectives (SLOs) at the cost of resource under-utilization and KV-cache transfer overheads. To address the limitations of these techniques, we propose RAPID-Serve: a technique to concurrently execute prefill and decode on the same GPU(s) to meet latency SLOs while maintaining high throughput and efficient resource utilization. Furthermore, we propose Adaptive Resource Management for runtime compute resource allocation, optionally leveraging CU masking (a fine-grained Compute Unit partitioning feature on AMD InstinctTM GPUs). RAPID-Serve provides up to 4.1x (average 1.7x) unconstrained throughput improvement and 32x and higher (average 4.9x) throughput improvement under SLO constraints, showing it as an effective strategy compared to the state-of-the-art approaches, particularly in resource-constrained environments.

During inference for transformer-based large language models (LLM), prefilling is the computation of the key-value (KV) cache for input tokens in the prompt prior to autoregressive generation. For longer input prompt lengths, prefilling will incur a significant overhead on decoding time. In this work, we highlight the following pitfall of prefilling: for batches containing high-varying prompt lengths, significant computation is wasted by the standard practice of padding sequences to the maximum length. As LLMs increasingly support longer context lengths, potentially up to 10 million tokens, variations in prompt lengths within a batch become more pronounced. To address this, we propose Prepacking, a simple yet effective method to optimize prefilling computation. To avoid redundant computation on pad tokens, prepacking combines prompts of varying lengths into a sequence and packs multiple sequences into a compact batch using a bin-packing algorithm. It then modifies the attention mask and positional encoding to compute multiple prefilled KV-caches for multiple prompts within a single sequence. On standard curated dataset containing prompts with varying lengths, we obtain a significant speed and memory efficiency improvements as compared to the default padding-based prefilling computation within Huggingface across a range of base model configurations and inference serving scenarios.

As large language models (LLMs) evolve to handle increasingly longer contexts, serving inference requests for context lengths in the range of millions of tokens presents unique challenges. While existing techniques are effective for training, they fail to address the unique challenges of inference, such as varying prefill and decode phases and their associated latency constraints - like Time to First Token (TTFT) and Time Between Tokens (TBT). Furthermore, there are no long context inference solutions that allow batching requests to increase the hardware utilization today. In this paper, we propose three key innovations for efficient interactive long context LLM inference, without resorting to any approximation: adaptive chunking to reduce prefill overheads in mixed batching, Sequence Pipeline Parallelism (SPP) to lower TTFT, and KV Cache Parallelism (KVP) to minimize TBT. These contributions are combined into a 3D parallelism strategy, enabling Mnemosyne to scale interactive inference to context lengths at least up to 10 million tokens with high throughput enabled with batching. To our knowledge, Mnemosyne is the first to be able to achieve support for 10 million long context inference efficiently, while satisfying production-grade SLOs on TBT (30ms) on contexts up to and including 10 million.

The "pretrain-then-finetune" paradigm is commonly adopted in the deployment of large language models. Low-Rank Adaptation (LoRA), a parameter-efficient fine-tuning method, is often employed to adapt a base model to a multitude of tasks, resulting in a substantial collection of LoRA adapters derived from one base model. We observe that this paradigm presents significant opportunities for batched inference during serving. To capitalize on these opportunities, we present S-LoRA, a system designed for the scalable serving of many LoRA adapters. S-LoRA stores all adapters in the main memory and fetches the adapters used by the currently running queries to the GPU memory. To efficiently use the GPU memory and reduce fragmentation, S-LoRA proposes Unified Paging. Unified Paging uses a unified memory pool to manage dynamic adapter weights with different ranks and KV cache tensors with varying sequence lengths. Additionally, S-LoRA employs a novel tensor parallelism strategy and highly optimized custom CUDA kernels for heterogeneous batching of LoRA computation. Collectively, these features enable S-LoRA to serve thousands of LoRA adapters on a single GPU or across multiple GPUs with a small overhead. Compared to state-of-the-art libraries such as HuggingFace PEFT and vLLM (with naive support of LoRA serving), S-LoRA can improve the throughput by up to 4 times and increase the number of served adapters by several orders of magnitude. As a result, S-LoRA enables scalable serving of many task-specific fine-tuned models and offers the potential for large-scale customized fine-tuning services.

In Large Language Model (LLM) inference, the output length of an LLM request is typically regarded as not known a priori. Consequently, most LLM serving systems employ a simple First-come-first-serve (FCFS) scheduling strategy, leading to Head-Of-Line (HOL) blocking and reduced throughput and service quality. In this paper, we reexamine this assumption -- we show that, although predicting the exact generation length of each request is infeasible, it is possible to predict the relative ranks of output lengths in a batch of requests, using learning to rank. The ranking information offers valuable guidance for scheduling requests. Building on this insight, we develop a novel scheduler for LLM inference and serving that can approximate the shortest-job-first (SJF) schedule better than existing approaches. We integrate this scheduler with the state-of-the-art LLM serving system and show significant performance improvement in several important applications: 2.8x lower latency in chatbot serving and 6.5x higher throughput in synthetic data generation. Our code is available at https://github.com/hao-ai-lab/vllm-ltr.git

Transformer-based large language models (LLMs) demonstrate impressive performance across various natural language processing tasks. Serving LLM inference for generating long contents, however, poses a challenge due to the enormous memory footprint of the transient state, known as the key-value (KV) cache, which scales with the sequence length and batch size. In this paper, we present InfiniGen, a novel KV cache management framework tailored for long-text generation, which synergistically works with modern offloading-based inference systems. InfiniGen leverages the key insight that a few important tokens that are essential for computing the subsequent attention layer in the Transformer can be speculated by performing a minimal rehearsal with the inputs of the current layer and part of the query weight and key cache of the subsequent layer. This allows us to prefetch only the essential KV cache entries (without fetching them all), thereby mitigating the fetch overhead from the host memory in offloading-based LLM serving systems. Our evaluation on several representative LLMs shows that InfiniGen improves the overall performance of a modern offloading-based system by up to 3.00x compared to prior KV cache management methods while offering substantially better model accuracy.

Long-context agentic workflows have emerged as a defining use case for large language models, making attention efficiency critical for both inference speed and serving cost. Sparse attention addresses this challenge effectively, and DeepSeek Sparse Attention (DSA) is a representative production-grade solution: a lightweight lightning indexer selects the top-k most relevant tokens per query, reducing core attention from O(L^2) to O(Lk). However, the indexer itself retains O(L^2) complexity and must run independently at every layer, despite the fact that the resulting top-k selections are highly similar across consecutive layers. We present IndexCache, which exploits this cross-layer redundancy by partitioning layers into a small set of Full layers that run their own indexers and a majority of Shared layers that simply reuse the nearest Full layer's top-k indices. We propose two complementary approaches to determine and optimize this configuration. Training-free IndexCache applies a greedy search algorithm that selects which layers to retain indexers by directly minimizing language modeling loss on a calibration set, requiring no weight updates. Training-aware IndexCache introduces a multi-layer distillation loss that trains each retained indexer against the averaged attention distributions of all layers it serves, enabling even simple interleaved patterns to match full-indexer accuracy. Experimental results on a 30B DSA model show that IndexCache can remove 75% of indexer computations with negligible quality degradation, achieving up to 1.82times prefill speedup and 1.48times decode speedup compared to standard DSA. These positive results are further confirmed by our preliminary experiments on the production-scale GLM-5 model (Figure 1).

BERT (Bidirectional Encoder Representations from Transformers) has revolutionized the field of natural language processing through its exceptional performance on numerous tasks. Yet, the majority of researchers have mainly concentrated on enhancements related to the model structure, such as relative position embedding and more efficient attention mechanisms. Others have delved into pretraining tricks associated with Masked Language Modeling, including whole word masking. DeBERTa introduced an enhanced decoder adapted for BERT's encoder model for pretraining, proving to be highly effective. We argue that the design and research around enhanced masked language modeling decoders have been underappreciated. In this paper, we propose several designs of enhanced decoders and introduce DrBERT (Decoder-refined BERT), a novel method for modeling training. Typically, a pretrained BERT model is fine-tuned for specific Natural Language Understanding (NLU) tasks. In our approach, we utilize the original BERT model as the encoder, making only changes to the decoder without altering the encoder. This approach does not necessitate extensive modifications to the model's architecture and can be seamlessly integrated into existing fine-tuning pipelines and services, offering an efficient and effective enhancement strategy. Compared to other methods, while we also incur a moderate training cost for the decoder during the pretraining process, our approach does not introduce additional training costs during the fine-tuning phase. We test multiple enhanced decoder structures after pretraining and evaluate their performance on the GLUE benchmark. Our results demonstrate that DrBERT, having only undergone subtle refinements to the model structure during pretraining, significantly enhances model performance without escalating the inference time and serving budget.

Generative Retrieval (GR) has emerged as a promising paradigm for modern search systems. Compared to multi-stage cascaded architecture, it offers advantages such as end-to-end joint optimization and high computational efficiency. OneSearch, as a representative industrial-scale deployed generative search framework, has brought significant commercial and operational benefits. However, its inadequate understanding of complex queries, inefficient exploitation of latent user intents, and overfitting to narrow historical preferences have limited its further performance improvement. To address these challenges, we propose OneSearch-V2, a latent reasoning enhanced self-distillation generative search framework. It contains three key innovations: (1) a thought-augmented complex query understanding module, which enables deep query understanding and overcomes the shallow semantic matching limitations of direct inference; (2) a reasoning-internalized self-distillation training pipeline, which uncovers users' potential yet precise e-commerce intentions beyond log-fitting through implicit in-context learning; (3) a behavior preference alignment optimization system, which mitigates reward hacking arising from the single conversion metric, and addresses personal preference via direct user feedback. Extensive offline evaluations demonstrate OneSearch-V2's strong query recognition and user profiling capabilities. Online A/B tests further validate its business effectiveness, yielding +3.98\% item CTR, +3.05\% buyer conversion rate, and +2.11\% order volume. Manual evaluation further confirms gains in search experience quality, with +1.65\% in page good rate and +1.37\% in query-item relevance. More importantly, OneSearch-V2 effectively mitigates common search system issues such as information bubbles and long-tail sparsity, without incurring additional inference costs or serving latency.

The rapid advancement in Large Language Models (LLMs) has markedly enhanced the capabilities of language understanding and generation. However, the substantial model size poses hardware challenges, affecting both memory size for serving and inference latency for token generation. To address those challenges, we propose Dependency-aware Semi-structured Sparsity (DaSS), a novel method for the recent prevalent SwiGLU-based LLMs pruning. Our approach incorporates structural dependency into the weight magnitude-based unstructured pruning. We introduce an MLP-specific pruning metric that evaluates the importance of each weight by jointly considering its magnitude and its corresponding MLP intermediate activation norms. DaSS facilitates a balance between the adaptability offered by unstructured pruning and the structural consistency inherent in dependency-based structured pruning. Empirical evaluations on Mistral and LLaMA2 model families demonstrate that DaSS not only outperforms both SparseGPT and Wanda in achieving hardware-friendly N:M sparsity patterns but also maintains the computational efficiency of Wanda.

The high computational and memory requirements of generative large language models (LLMs) make it challenging to serve them quickly and cheaply. This paper introduces SpecInfer, an LLM serving system that accelerates generative LLM inference with speculative inference and token tree verification. A key insight behind SpecInfer is to combine various collectively boost-tuned small language models to jointly predict the LLM's outputs; the predictions are organized as a token tree, whose nodes each represent a candidate token sequence. The correctness of all candidate token sequences represented by a token tree is verified by the LLM in parallel using a novel tree-based parallel decoding mechanism. SpecInfer uses an LLM as a token tree verifier instead of an incremental decoder, which significantly reduces the end-to-end latency and computational requirement for serving generative LLMs while provably preserving model quality.

Large language models (LLMs), while driving a new wave of interactive AI applications across numerous domains, suffer from high inference costs and heavy cloud dependency. Motivated by the redundancy phenomenon in linguistics, we propose a progressive inference paradigm over cloud and edge, i.e., firstly generating the sketch of the answer by LLMs at cloud, and then conducting parallel extension to fill in details by small models (SLMs) at edge. Progressive inference offers potential benefits to improve throughput and reduce inference latency while facing key implementation challenges, including decreased response quality from SLMs, a tradeoff between the brevity and comprehensiveness of sketches, as well as increased latency caused by network transmission and edge inference. In this work, we propose and implement PICE, an LLM serving system with semantic-level cloud-edge collaboration, enhancing inference throughput and quality through dynamic inference task scheduling, ensemble learning, and parallel edge inference. Extensive testbed experiments illustrate that our approach achieves 1.5-2times throughput enhancement and up to 43% latency reduction, while also potentially enhancing the quality compared to SOTA systems.

Parameter-efficient finetuning (PEFT) is a widely used technique to adapt large language models for different tasks. Service providers typically create separate systems for users to perform PEFT model finetuning and inference tasks. This is because existing systems cannot handle workloads that include a mix of inference and PEFT finetuning requests. As a result, shared GPU resources are underutilized, leading to inefficiencies. To address this problem, we present FlexLLM, the first system that can serve inference and parameter-efficient finetuning requests in the same iteration. Our system leverages the complementary nature of these two tasks and utilizes shared GPU resources to run them jointly, using a method called co-serving. To achieve this, FlexLLM introduces a novel token-level finetuning mechanism, which breaks down the finetuning computation of a sequence into smaller token-level computations and uses dependent parallelization and graph pruning, two static compilation optimizations, to minimize the memory overhead and latency for co-serving. Compared to existing systems, FlexLLM's co-serving approach reduces the activation GPU memory overhead by up to 8x, and the end-to-end GPU memory requirement of finetuning by up to 36% while maintaining a low inference latency and improving finetuning throughput. For example, under a heavy inference workload, FlexLLM can still preserve more than 80% of the peak finetuning throughput, whereas existing systems cannot make any progress with finetuning. The source code of FlexLLM is publicly available at https://github.com/flexflow/FlexFlow.

As large-scale visual-document corpora such as arXiv papers and enterprise PDFs continue to grow, visual-document retrieval has gained increasing attention; yet it still lacks a deployable system that lexically indexes visual documents to serve queries without neural encoding at scale. Existing methods either achieve strong retrieval quality with VLM-based dense or multi-vector models but require neural query encoding at serving time, or avoid query encoding with OCR- or caption-based BM25 at the cost of time-consuming text extraction or generation. To fill this missing serving regime, we present V-SPLADE, an inference-free sparse retriever for visual-document retrieval. However, such inference-free multimodal learned sparse retrieval systems remain underexplored and have not yet shown dense-level effectiveness under high sparsity. We attribute this limitation to a lexical grounding problem: visual sparse representations often fail to capture the lexical content embedded in document images. To address this problem, we introduce caption-gated token supervision, a training-only signal that uses VLM-generated captions as lexical cues to activate retrieval-relevant vocabulary dimensions. With this supervision, V-SPLADE improves average NDCG@5 across six visual-document retrieval benchmarks by +13.8pp over the same-scale dense baseline and by up to +6.3pp over OCR- or caption-based BM25 baselines. On an 18.7M-document corpus, it more than doubles R@5 over the same-scale dense baseline and further improves competing retrievers through score fusion by up to +2.4pp R@5. Code will be released soon at https://github.com/naver/v-splade.

The rapid evolution of large language models (LLMs) has unlocked their capabilities in advanced reasoning tasks like mathematical problem-solving, code generation, and legal analysis. Central to this progress are inference-time reasoning algorithms, which refine outputs by exploring multiple solution paths, at the cost of increasing compute demands and response latencies. Existing serving systems fail to adapt to the scaling behaviors of these algorithms or the varying difficulty of queries, leading to inefficient resource use and unmet latency targets. We present Dynasor, a system that optimizes inference-time compute for LLM reasoning queries. Unlike traditional engines, Dynasor tracks and schedules requests within reasoning queries and uses Certaindex, a proxy that measures statistical reasoning progress based on model certainty, to guide compute allocation dynamically. Dynasor co-adapts scheduling with reasoning progress: it allocates more compute to hard queries, reduces compute for simpler ones, and terminates unpromising queries early, balancing accuracy, latency, and cost. On diverse datasets and algorithms, Dynasor reduces compute by up to 50% in batch processing and sustaining 3.3x higher query rates or 4.7x tighter latency SLOs in online serving.

Large model inference is shifting from cloud to edge due to concerns about the privacy of user interaction data. However, edge devices often struggle with limited computing power, memory, and bandwidth, requiring collaboration across multiple devices to run and speed up LLM inference. Pipeline parallelism, the mainstream solution, is inefficient for single-user scenarios, while tensor parallelism struggles with frequent communications. In this paper, we argue that tensor parallelism can be more effective than pipeline on low-resource devices, and present a compute- and memory-efficient tensor parallel inference system, named TPI-LLM, to serve 70B-scale models. TPI-LLM keeps sensitive raw data local in the users' devices and introduces a sliding window memory scheduler to dynamically manage layer weights during inference, with disk I/O latency overlapped with the computation and communication. This allows larger models to run smoothly on memory-limited devices. We analyze the communication bottleneck and find that link latency, not bandwidth, emerges as the main issue, so a star-based allreduce algorithm is implemented. Through extensive experiments on both emulated and real testbeds, TPI-LLM demonstrated over 80% less time-to-first-token and token latency compared to Accelerate, and over 90% compared to Transformers and Galaxy, while cutting the peak memory footprint of Llama 2-70B by 90%, requiring only 3.1 GB of memory for 70B-scale models.

Recent advances in leveraging the agentic paradigm of large language models (LLMs) utilization have significantly enhanced Text-to-SQL capabilities, enabling users without specialized database expertise to query data intuitively. However, deploying these agentic LLM-based Text-to-SQL systems in production poses substantial challenges due to their inherently multi-stage workflows, stringent latency constraints, and potentially heterogeneous GPU infrastructure in enterprise environments. Current LLM serving frameworks lack effective mechanisms for handling interdependent inference tasks, dynamic latency variability, and resource heterogeneity, leading to suboptimal performance and frequent service-level objective (SLO) violations. In this paper, we introduce HEXGEN-TEXT2SQL, a novel framework designed explicitly to schedule and execute agentic multi-stage LLM-based Text-to-SQL workflows on heterogeneous GPU clusters that handle multi-tenant end-to-end queries. HEXGEN-TEXT2SQL introduce a hierarchical scheduling approach combining global workload-balanced task dispatching and local adaptive urgency-guided prioritization, guided by a systematic analysis of agentic Text-to-SQL workflows. Additionally, we propose a lightweight simulation-based method for tuning critical scheduling hyperparameters, further enhancing robustness and adaptability. Our extensive evaluation on realistic Text-to-SQL benchmarks demonstrates that HEXGEN-TEXT2SQL significantly outperforms state-of-the-art LLM serving frameworks. Specifically, HEXGEN-TEXT2SQL reduces latency deadlines by up to 1.67times (average: 1.41times) and improves system throughput by up to 1.75times (average: 1.65times) compared to vLLM under diverse, realistic workload conditions. Our code is available at https://github.com/Relaxed-System-Lab/Hexgen-Flow.

Novel View Synthesis (NVS) is the task of generating new images of a scene from viewpoints that were not part of the original input. Diffusion-based NVS can generate high-quality, temporally consistent images, however, remains computationally prohibitive. Conversely, regression-based NVS offers suboptimal generation quality despite requiring significantly lower compute; leaving the design objective of a high-quality, inference-efficient NVS framework an open challenge. To close this critical gap, we present Sphinx, a training-free hybrid inference framework that achieves diffusion-level fidelity at a significantly lower compute. Sphinx proposes to use regression-based fast initialization to guide and reduce the denoising workload for the diffusion model. Additionally, it integrates selective refinement with adaptive noise scheduling, allowing more compute to uncertain regions and frames. This enables Sphinx to provide flexible navigation of the performance-quality trade-off, allowing adaptation to latency and fidelity requirements for dynamically changing inference scenarios. Our evaluation shows that Sphinx achieves an average 1.8x speedup over diffusion model inference with negligible perceptual degradation of less than 5%, establishing a new Pareto frontier between quality and latency in NVS serving.

Existing LLM training and inference frameworks struggle in boosting efficiency with sparsity while maintaining the integrity of context and model architecture. Inspired by the sharding concept in database and the fact that attention parallelizes over heads on accelerators, we propose Sparsely-Sharded (S2) Attention, an attention algorithm that allocates heterogeneous context partitions for different attention heads to divide and conquer. S2-Attention enforces each attention head to only attend to a partition of contexts following a strided sparsity pattern, while the full context is preserved as the union of all the shards. As attention heads are processed in separate thread blocks, the context reduction for each head can thus produce end-to-end speed-up and memory reduction. At inference, LLMs trained with S2-Attention can then take the KV cache reduction as free meals with guaranteed model quality preserve. In experiments, we show S2-Attentioncan provide as much as (1) 25.3X wall-clock attention speed-up over FlashAttention-2, resulting in 6X reduction in end-to-end training time and 10X inference latency, (2) on-par model training quality compared to default attention, (3)perfect needle retrieval accuracy over 32K context window. On top of the algorithm, we build DKernel, an LLM training and inference kernel library that allows users to customize sparsity patterns for their own models. We open-sourced DKerneland make it compatible with Megatron, Pytorch, and vLLM.

Large language models (LLMs) have surged in popularity and are extensively used in commercial applications, where the efficiency of model serving is crucial for the user experience. Most current research focuses on optimizing individual sub-procedures, e.g. local inference and communication, however, there is no comprehensive framework that provides a holistic system view for optimizing LLM serving in an end-to-end manner. In this work, we conduct a detailed analysis to identify major bottlenecks that impact end-to-end latency in LLM serving systems. Our analysis reveals that a comprehensive LLM serving endpoint must address a series of efficiency bottlenecks that extend beyond LLM inference. We then propose ScaleLLM, an optimized system for resource-efficient LLM serving. Our extensive experiments reveal that with 64 concurrent requests, ScaleLLM achieves a 4.3x speed up over vLLM and outperforms state-of-the-arts with 1.5x higher throughput.

Reducing the inference latency of large language models (LLMs) is crucial, and speculative decoding (SD) stands out as one of the most effective techniques. Rather than letting the LLM generate all tokens directly, speculative decoding employs effective proxies to predict potential outputs, which are then verified by the LLM without compromising the generation quality. Yet, deploying SD in real online LLM serving systems (with continuous batching) does not always yield improvement -- under higher request rates or low speculation accuracy, it paradoxically increases latency. Furthermore, there is no best speculation length work for all workloads under different system loads. Based on the observations, we develop a dynamic framework SmartSpec. SmartSpec dynamically determines the best speculation length for each request (from 0, i.e., no speculation, to many tokens) -- hence the associated speculative execution costs -- based on a new metric called goodput, which characterizes the current observed load of the entire system and the speculation accuracy. We show that SmartSpec consistently reduces average request latency by up to 3.2x compared to non-speculative decoding baselines across different sizes of target models, draft models, request rates, and datasets. Moreover, SmartSpec can be applied to different styles of speculative decoding, including traditional, model-based approaches as well as model-free methods like prompt lookup and tree-style decoding.

Deploying a large language model (LLM) inference service remains costly because centralized serving depends on specialized GPU clusters and high-bandwidth interconnects in datacenters. An appealing alternative is to leverage collaborative decentralized GPU pools. However, heterogeneity in GPU and limited interconnected network bandwidth, along with potentially dynamic availability, make efficient scheduling the central challenge in this scenario. In this paper, we present Parallax, a decentralized LLM serving system that turns a pool of heterogeneous GPUs into an efficient inference platform via a two-phase scheduler. Parallax decomposes planning into (i) model allocation, which places layers of each replica across diverse GPUs to jointly optimize latency and throughput under memory and link-bandwidth constraints, and (ii) request-time GPU pipeline selection, which stitches layers from different replicas into end-to-end execution chains that balance load and adapt to current conditions. We implement Parallax and evaluate it on open-source LLMs deployed over real volunteer nodes. Parallax consistently reduces latency and increases throughput relative to decentralized baselines, demonstrating that principled scheduling can make volunteer compute a practical, affordable substrate for LLM inference. Github Repo at: https://github.com/GradientHQ/parallax.

This paper documents our characterization study and practices for serving text-to-image requests with stable diffusion models in production. We first comprehensively analyze inference request traces for commercial text-to-image applications. It commences with our observation that add-on modules, i.e., ControlNets and LoRAs, that augment the base stable diffusion models, are ubiquitous in generating images for commercial applications. Despite their efficacy, these add-on modules incur high loading overhead, prolong the serving latency, and swallow up expensive GPU resources. Driven by our characterization study, we present SwiftDiffusion, a system that efficiently generates high-quality images using stable diffusion models and add-on modules. To achieve this, SwiftDiffusion reconstructs the existing text-to-image serving workflow by identifying the opportunities for parallel computation and distributing ControlNet computations across multiple GPUs. Further, SwiftDiffusion thoroughly analyzes the dynamics of image generation and develops techniques to eliminate the overhead associated with LoRA loading and patching while preserving the image quality. Last, SwiftDiffusion proposes specialized optimizations in the backbone architecture of the stable diffusion models, which are also compatible with the efficient serving of add-on modules. Compared to state-of-the-art text-to-image serving systems, SwiftDiffusion reduces serving latency by up to 5x and improves serving throughput by up to 2x without compromising image quality.

Expert-Specialized Fine-Tuning (ESFT) adapts Mixture-of-Experts (MoE) large language models to enhance their task-specific performance by selectively tuning the top-activated experts for the task. Serving these fine-tuned models at scale is challenging: deploying merged models in isolation is prohibitively resource-hungry, while existing multi-adapter serving systems with LoRA-style additive updates are incompatible with ESFT's expert-oriented paradigm. We present ExpertWeave, a system that serves multiple ESFT adapters concurrently over a single shared MoE base model, drastically reducing the memory footprint and improving resource utilization. To seamlessly integrate into existing inference pipelines for MoE models with non-intrusive modifications and minimal latency overhead, ExpertWeave introduces a virtual-memory-assisted expert weight manager that co-locates base-model and adapter experts without incurring memory overhead from fragmentation, and a fused kernel for batched rerouting to enable lightweight redirection of tokens to the appropriate experts at runtime. Our evaluations show that ExpertWeave can simultaneously serve multiple adapters of a 16B MoE model on a single accelerator where the baseline runs out of memory, or provides up to 94x more KV cache capacity and achieves up to 18% higher throughput while using comparable resources, all without compromising model accuracy. ExpertWeave maintains low overhead even when scaling to 20 adapters, with a 4-11% latency increase compared with serving the base model alone. Source code will be released soon.

Serving large language models (LLMs) in production can incur substantial costs, which has prompted recent advances in inference system optimizations. Today, these systems are evaluated against conventional latency and throughput metrics (eg. TTFT, TBT, Normalised Latency and TPOT). However, these metrics fail to fully capture the nuances of LLM inference, leading to an incomplete assessment of user-facing performance crucial for real-time applications such as chat and translation. In this paper, we first identify the pitfalls of current performance metrics in evaluating LLM inference systems. We then propose Etalon, a comprehensive performance evaluation framework that includes fluidity-index -- a novel metric designed to reflect the intricacies of the LLM inference process and its impact on real-time user experience. Finally, we evaluate various existing open-source platforms and model-as-a-service offerings using Etalon, discussing their strengths and weaknesses. Etalon is available at https://github.com/project-etalon/etalon.

Each LLM serving request goes through two phases. The first is prefill which processes the entire input prompt to produce one output token and the second is decode which generates the rest of output tokens, one-at-a-time. Prefill iterations have high latency but saturate GPU compute due to parallel processing of the input prompt. In contrast, decode iterations have low latency but also low compute utilization because a decode iteration processes only a single token per request. This makes batching highly effective for decodes and consequently for overall throughput. However, batching multiple requests leads to an interleaving of prefill and decode iterations which makes it challenging to achieve both high throughput and low latency. We introduce an efficient LLM inference scheduler Sarathi-Serve inspired by the techniques we originally proposed for optimizing throughput in Sarathi. Sarathi-Serve leverages chunked-prefills from Sarathi to create stall-free schedules that can add new requests in a batch without pausing ongoing decodes. Stall-free scheduling unlocks the opportunity to improve throughput with large batch sizes while minimizing the effect of batching on latency. Our evaluation shows that Sarathi-Serve improves serving throughput within desired latency SLOs of Mistral-7B by up to 2.6x on a single A100 GPU and up to 6.9x for Falcon-180B on 8 A100 GPUs over Orca and vLLM.

Six-bit quantization (FP6) can effectively reduce the size of large language models (LLMs) and preserve the model quality consistently across varied applications. However, existing systems do not provide Tensor Core support for FP6 quantization and struggle to achieve practical performance improvements during LLM inference. It is challenging to support FP6 quantization on GPUs due to (1) unfriendly memory access of model weights with irregular bit-width and (2) high runtime overhead of weight de-quantization. To address these problems, we propose TC-FPx, the first full-stack GPU kernel design scheme with unified Tensor Core support of float-point weights for various quantization bit-width. We integrate TC-FPx kernel into an existing inference system, providing new end-to-end support (called FP6-LLM) for quantized LLM inference, where better trade-offs between inference cost and model quality are achieved. Experiments show that FP6-LLM enables the inference of LLaMA-70b using only a single GPU, achieving 1.69x-2.65x higher normalized inference throughput than the FP16 baseline. The source code will be publicly available soon.

LLMs are seeing growing use for applications such as document analysis and summarization which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference. Quantization is a promising approach for compressing KV cache activations; however, existing solutions fail to represent activations accurately in ultra-low precisions, such as sub-4-bit. In this work, we present KVQuant, which addresses this problem by incorporating novel methods for quantizing cached KV activations, including: (i) Per-Channel Key Quantization, where we adjust the dimension along which we quantize the Key activations to better match the distribution; (ii) Pre-RoPE Key Quantization, where we quantize Key activations before the rotary positional embedding to mitigate its impact on quantization; (iii) Non-Uniform KV Cache Quantization, where we derive per-layer sensitivity-weighted non-uniform datatypes that better represent the distributions; (iv) Per-Vector Dense-and-Sparse Quantization, where we isolate outliers separately for each vector to minimize skews in quantization ranges; and (v) Q-Norm, where we normalize quantization centroids in order to mitigate distribution shift, providing additional benefits for 2-bit quantization. By applying our method to the LLaMA, LLaMA-2, and Mistral models, we achieve <0.1 perplexity degradation with 3-bit quantization on both Wikitext-2 and C4, outperforming existing approaches. Our method enables serving the LLaMA-7B model with a context length of up to 1 million on a single A100-80GB GPU and up to 10 million on an 8-GPU system.

Serving Large Language Models (LLMs) is a GPU-intensive task where traditional autoscalers fall short, particularly for modern Prefill-Decode (P/D) disaggregated architectures. This architectural shift, while powerful, introduces significant operational challenges, including inefficient use of heterogeneous hardware, network bottlenecks, and critical imbalances between prefill and decode stages. We introduce HeteroScale, a coordinated autoscaling framework that addresses the core challenges of P/D disaggregated serving. HeteroScale combines a topology-aware scheduler that adapts to heterogeneous hardware and network constraints with a novel metric-driven policy derived from the first large-scale empirical study of autoscaling signals in production. By leveraging a single, robust metric to jointly scale prefill and decode pools, HeteroScale maintains architectural balance while ensuring efficient, adaptive resource management. Deployed in a massive production environment on tens of thousands of GPUs, HeteroScale has proven its effectiveness, increasing average GPU utilization by a significant 26.6 percentage points and saving hundreds of thousands of GPU-hours daily, all while upholding stringent service level objectives.

Serving large language models (LLMs) at scale necessitates efficient key-value (KV) cache management. KV caches can be reused across conversation turns via shared-prefix prompts that are common in iterative code editing and chat. However, stale caches consume scarce GPU memory, require offloading, or force recomputation. We present KVTC, a lightweight transform coder that compresses KV caches for compact on-GPU and off-GPU storage. Drawing on classical media compression, KVTC combines PCA-based feature decorrelation, adaptive quantization, and entropy coding. It requires only a brief initial calibration and leaves model parameters unchanged. By exploiting redundancies in KV caches, KVTC achieves up to 20times compression while maintaining reasoning and long-context accuracy, and 40times or higher for specific use cases. We test KVTC with Llama 3, Mistral NeMo, and R1-Qwen 2.5 models across benchmarks including AIME25, LiveCodeBench, GSM8K, MMLU, Qasper, RULER, and MATH-500. It consistently outperforms inference-time baselines such as token eviction, quantization, and SVD-based methods, while achieving higher compression ratios. These results support KVTC as a practical building block for memory-efficient LLM serving with reusable KV caches.

Large language model (LLM) inference workload dominates a wide variety of modern AI applications, ranging from multi-turn conversation to document analysis. Balancing fairness and efficiency is critical for managing diverse client workloads with varying prefix patterns. Unfortunately, existing fair scheduling algorithms for LLM serving, such as Virtual Token Counter (VTC), fail to take prefix locality into consideration and thus suffer from poor performance. On the other hand, locality-aware scheduling algorithms in existing LLM serving frameworks tend to maximize the prefix cache hit rate without considering fair sharing among clients. This paper introduces the first locality-aware fair scheduling algorithm, Deficit Longest Prefix Match (DLPM), which can maintain a high degree of prefix locality with a fairness guarantee. We also introduce a novel algorithm, Double Deficit LPM (D^2LPM), extending DLPM for the distributed setup that can find a balance point among fairness, locality, and load-balancing. Our extensive evaluation demonstrates the superior performance of DLPM and D^2LPM in ensuring fairness while maintaining high throughput (up to 2.87times higher than VTC) and low per-client (up to 7.18times lower than state-of-the-art distributed LLM serving system) latency.

AI agents execute tens to hundreds of chained LLM calls per task, yet GPU schedulers treat each call as independent, discarding gigabytes of intermediate state between steps and inflating end-to-end latency by 3-8x. We argue that this request-level abstraction is fundamentally mismatched to compound AI workloads, and propose a shift to program-level scheduling: treating the entire agent workflow (not individual inference calls) as the first-class schedulable unit. We present SAGA, a distributed scheduler that implements this abstraction through three mechanisms: (1) Agent Execution Graphs that capture workflow structure to predict KV cache reuse across tool-call boundaries, achieving within 1.31x of Bélády's optimal offline policy; (2) session-affinity batching with work stealing that co-locates correlated requests while maintaining global load balance; and (3) Agent Fair Share, a task-completion-time fairness metric with provable bounded-deviation guarantees. On a 64-GPU cluster serving SWE-bench coding agents and WebArena browser tasks, SAGA reduces task completion time by 1.64x (geometric mean, p < 0.001) over vLLM v0.15.1 with prefix caching and affinity routing, while improving GPU memory utilization by 1.22x and achieving 99.2% SLO attainment under multi-tenant interference. These latency gains come at a quantified cost: approximately 30% lower peak throughput than throughput-optimal batch scheduling, a tradeoff appropriate for the latency-sensitive interactive deployments that dominate compound AI usage. Our results demonstrate that workflow-aware scheduling is essential for efficient compound AI serving.

Realistic evaluation of LLM serving systems requires online workloads, dynamic arrivals, queueing, and the serving engine's local scheduling for execution batching, but running such experiments on GPUs is expensive. Existing simulators reduce this cost, but often operate offline or in time-warped mode, re-implement serving-engine schedulers, or require accurate operator/kernel-level latency models. We present LLM-Emu, a serving-native emulator for vLLM that preserves the production HTTP, scheduling, KV-cache, and output-processing paths while replacing only GPU forward execution with profile-sampled latency and synthetic output tokens. Tested on two different GPUs, four model variants, two model families, two attention backends, and both Poisson and bursty ShareGPT workloads, LLM-Emu closely tracks real vLLM serving behavior: TPOT and ITL stay within 4.8% absolute error, E2E latency within 5.3%, and output throughput within 1.9%; TTFT is less stable, with maximum error 10.4%, reflecting its sensitivity to admission and queue state. These results suggest that lightweight, serving-native emulation can support practical online experimentation for LLM-serving systems. LLM-Emu is open sourced at https://github.com/AKafakA/llm-emu.

Large Language Models (LLMs)-based hybrid retrieval uses LLMs to encode queries and documents into low-dimensional dense or high-dimensional sparse vectors. It retrieves documents relevant to search queries based on vector similarities. Documents are pre-encoded offline, while queries arrive in real-time, necessitating an efficient online query encoder. Although LLMs significantly enhance retrieval capabilities, serving deeply parameterized LLMs slows down query inference throughput and increases demands for online deployment resources. In this paper, we propose LightRetriever, a novel LLM-based hybrid retriever with extremely lightweight query encoders. Our method retains a full-sized LLM for document encoding, but reduces the workload of query encoding to no more than an embedding lookup. Compared to serving a full-sized LLM on an H800 GPU, our approach achieves over a 1000x speedup for query inference with GPU acceleration, and even a 20x speedup without GPU. Experiments on large-scale retrieval benchmarks demonstrate that our method generalizes well across diverse retrieval tasks, retaining an average of 95% full-sized performance.

Training and serving long-context large language models (LLMs) incurs substantial overhead. To address this, two critical steps are often required: a pretrained LLM typically undergoes a separate stage for context length extension by training on long-context data, followed by architectural modifications to reduce the overhead of KV cache during serving. This paper argues that integrating length extension with a GPU-friendly KV cache reduction architecture not only reduces training overhead during length extension, but also achieves better long-context performance. This leads to our proposed LongGen, which finetunes a pretrained LLM into an efficient architecture during length extension. LongGen builds on three key insights: (1) Sparse attention patterns, such as window attention (attending to recent tokens), attention sink (initial ones), and blockwise sparse attention (strided token blocks) are well-suited for building efficient long-context models, primarily due to their GPU-friendly memory access patterns, enabling efficiency gains not just theoretically but in practice as well. (2) It is essential for the model to have direct access to all tokens. A hybrid architecture with 1/3 full attention layers and 2/3 efficient ones achieves a balanced trade-off between efficiency and long-context performance. (3) Lightweight training on 5B long-context data is sufficient to extend the hybrid model's context length from 4K to 128K. We evaluate LongGen on both Llama-2 7B and Llama-2 70B, demonstrating its effectiveness across different scales. During training with 128K-long contexts, LongGen achieves 1.55x training speedup and reduces wall-clock time by 36%, compared to a full-attention baseline. During inference, LongGen reduces KV cache memory by 62%, achieving 1.67x prefilling speedup and 1.41x decoding speedup.

Transformer-based large language models (LLMs) exhibit impressive performance in generative tasks but introduce significant challenges in real-world serving due to inefficient use of the expensive, computation-optimized accelerators. This mismatch arises from the autoregressive nature of LLMs, where the generation phase comprises operators with varying resource demands. Specifically, the attention operator is memory-intensive, exhibiting a memory access pattern that clashes with the strengths of modern accelerators, especially as context length increases. To enhance the efficiency and cost-effectiveness of LLM serving, we introduce the concept of attention offloading. This approach leverages a collection of cheap, memory-optimized devices for the attention operator while still utilizing high-end accelerators for other parts of the model. This heterogeneous setup ensures that each component is tailored to its specific workload, maximizing overall performance and cost efficiency. Our comprehensive analysis and experiments confirm the viability of splitting the attention computation over multiple devices. Also, the communication bandwidth required between heterogeneous devices proves to be manageable with prevalent networking technologies. To further validate our theory, we develop Lamina, an LLM inference system that incorporates attention offloading. Experimental results indicate that Lamina can provide 1.48x-12.1x higher estimated throughput per dollar than homogeneous solutions.

The performance of multi-turn, agentic LLM inference is increasingly dominated by KV-Cache storage I/O rather than computation. In prevalent disaggregated architectures, loading the massive KV-Cache from external storage creates a fundamental imbalance: storage NICs on prefill engines become bandwidth-saturated, while those on decoding engines remain idle. This asymmetry severely constrains overall system throughput. We present DualPath, an inference system that breaks this bottleneck by introducing dual-path KV-Cache loading. Beyond the traditional storage-to-prefill path, DualPath enables a novel storage-to-decode path, in which the KV-Cache is loaded into decoding engines and then efficiently transferred to prefill engines via RDMA over the compute network. DualPath combines this optimized data path -- which inherently avoids network congestion and avoids interference with latency-critical model execution communications -- with a global scheduler that dynamically balances load across prefill and decode engines. Our evaluation on three models with production agentic workloads demonstrates that DualPath improves offline inference throughput by up to 1.87times on our in-house inference system. It can also improve online serving throughput by an average factor of 1.96times without violating SLO.

This paper introduces PowerInfer, a high-speed Large Language Model (LLM) inference engine on a personal computer (PC) equipped with a single consumer-grade GPU. The key underlying the design of PowerInfer is exploiting the high locality inherent in LLM inference, characterized by a power-law distribution in neuron activation. This distribution indicates that a small subset of neurons, termed hot neurons, are consistently activated across inputs, while the majority, cold neurons, vary based on specific inputs. PowerInfer exploits such an insight to design a GPU-CPU hybrid inference engine: hot-activated neurons are preloaded onto the GPU for fast access, while cold-activated neurons are computed on the CPU, thus significantly reducing GPU memory demands and CPU-GPU data transfers. PowerInfer further integrates adaptive predictors and neuron-aware sparse operators, optimizing the efficiency of neuron activation and computational sparsity. Evaluation shows that PowerInfer attains an average token generation rate of 13.20 tokens/s, with a peak of 29.08 tokens/s, across various LLMs (including OPT-175B) on a single NVIDIA RTX 4090 GPU, only 18% lower than that achieved by a top-tier server-grade A100 GPU. This significantly outperforms llama.cpp by up to 11.69x while retaining model accuracy.

Efficient use of GPU memory is essential for high throughput LLM inference. Prior systems reserved memory for the KV-cache ahead-of-time, resulting in wasted capacity due to internal fragmentation. Inspired by OS-based virtual memory systems, vLLM proposed PagedAttention to enable dynamic memory allocation for KV-cache. This approach eliminates fragmentation, enabling high-throughput LLM serving with larger batch sizes. However, to be able to allocate physical memory dynamically, PagedAttention changes the layout of KV-cache from contiguous virtual memory to non-contiguous virtual memory. This change requires attention kernels to be rewritten to support paging, and serving framework to implement a memory manager. Thus, the PagedAttention model leads to software complexity, portability issues, redundancy and inefficiency. In this paper, we propose vAttention for dynamic KV-cache memory management. In contrast to PagedAttention, vAttention retains KV-cache in contiguous virtual memory and leverages low-level system support for demand paging, that already exists, to enable on-demand physical memory allocation. Thus, vAttention unburdens the attention kernel developer from having to explicitly support paging and avoids re-implementation of memory management in the serving framework. We show that vAttention enables seamless dynamic memory management for unchanged implementations of various attention kernels. vAttention also generates tokens up to 1.97x faster than vLLM, while processing input prompts up to 3.92x and 1.45x faster than the PagedAttention variants of FlashAttention and FlashInfer.

Retrieval-Augmented Generation (RAG) is a critical paradigm for building reliable, knowledge-intensive Large Language Model (LLM) applications. However, the multi-stage pipeline (retrieve, generate) and unique workload characteristics (e.g., knowledge dependency) of RAG systems pose significant challenges for serving performance optimization. Existing generic LLM inference traces fail to capture these RAG-specific dynamics, creating a significant performance gap between academic research and real-world deployment. To bridge this gap, this paper introduces RAGPulse, an open-source RAG workload trace dataset. This dataset was collected from an university-wide Q&A system serving that has served more than 40,000 students and faculties since April 2024. We detail RAGPulse's system architecture, its privacy-preserving hash-based data format, and provide an in-depth statistical analysis. Our analysis reveals that real-world RAG workloads exhibit significant temporal locality and a highly skewed hot document access pattern. RAGPulse provides a high-fidelity foundation for researchers to develop and validate novel optimization strategies for RAG systems, such as content-aware batching and retrieval caching, ultimately enhancing the efficiency and reliability of RAG services. The code is available at https://github.com/flashserve/RAGPulse.

Speculative decoding (SD) is a widely used approach for accelerating decode-heavy LLM inference workloads. While online inference workloads are highly dynamic, existing SD systems are rigid and take a coarse-grained approach to SD management. They typically set the speculative token length for an entire batch and serialize the execution of the draft and verification phases. Consequently, these systems fall short at adapting to volatile online inference traffic. Under low load, they exhibit prolonged latency because the draft phase blocks the verification phase for the entire batch, leaving GPU computing resources underutilized. Conversely, under high load, they waste computation on rejected tokens during the verification phase, overloading GPU resources. We introduce FASER, a novel system that features fine-grained SD phase management. First, FASER minimizes computational waste by dynamically adjusting the speculative length for each request within a continuous batch and by performing early pruning of rejected tokens inside the verification phase. Second, FASER breaks the verification phase into frontiers, or chunks, to overlap them with the draft phase. This overlap is achieved via fine-grained spatial multiplexing with minimal resource interference. Our FASER prototype in vLLM improves throughput by up to 53% and reduces latency by up to 1.92times compared to state-of-the-art systems.

AI agent inference is driving an inference heavy datacenter future and exposes bottlenecks beyond compute - especially memory capacity, memory bandwidth and high-speed interconnect. We introduce two metrics - Operational Intensity (OI) and Capacity Footprint (CF) - that jointly explain regimes the classic roofline analysis misses, including the memory capacity wall. Across agentic workflows (chat, coding, web use, computer use) and base model choices (GQA/MLA, MoE, quantization), OI/CF can shift dramatically, with long context KV cache making decode highly memory bound. These observations motivate disaggregated serving and system level heterogeneity: specialized prefill and decode accelerators, broader scale up networking, and decoupled compute-memory enabled by optical I/O. We further hypothesize agent-hardware co design, multiple inference accelerators within one system, and high bandwidth, large capacity memory disaggregation as foundations for adaptation to evolving OI/CF. Together, these directions chart a path to sustain efficiency and capability for large scale agentic AI inference.

Large language models (LLMs) often incorporate multiple text chunks in their inputs to provide the necessary contexts. To speed up the prefill of the long LLM inputs, one can pre-compute the KV cache of a text and re-use the KV cache when the context is reused as the prefix of another LLM input. However, the reused text chunks are not always the input prefix, and when they are not, their precomputed KV caches cannot be directly used since they ignore the text's cross-attention with the preceding text in the LLM input. Thus, the benefits of reusing KV caches remain largely unrealized. This paper tackles just one question: when an LLM input contains multiple text chunks, how to quickly combine their precomputed KV caches in order to achieve the same generation quality as the expensive full prefill (i.e., without reusing KV cache)? We present CacheBlend, a scheme that reuses the pre-computed KV caches, regardless prefix or not, and selectively recomputes the KV values of a small subset of tokens to partially update each reused KV cache. In the meantime,the small extra delay for recomputing some tokens can be pipelined with the retrieval of KV caches within the same job,allowing CacheBlend to store KV caches in slower devices with more storage capacity while retrieving them without increasing the inference delay. By comparing CacheBlend with the state-of-the-art KV cache reusing schemes on three open-source LLMs of various sizes and four popular benchmark datasets of different tasks, we show that CacheBlend reduces time-to-first-token (TTFT) by 2.2-3.3X and increases the inference throughput by 2.8-5X, compared with full KV recompute, without compromising generation quality or incurring more storage cost.

Machine learning (ML) inference platforms are tasked with balancing two competing goals: ensuring high throughput given many requests, and delivering low-latency responses to support interactive applications. Unfortunately, existing platform knobs (e.g., batch sizes) fail to ease this fundamental tension, and instead only enable users to harshly trade off one property for the other. This paper explores an alternate strategy to taming throughput-latency tradeoffs by changing the granularity at which inference is performed. We present Apparate, a system that automatically applies and manages early exits (EEs) in ML models, whereby certain inputs can exit with results at intermediate layers. To cope with the time-varying overhead and accuracy challenges that EEs bring, Apparate repurposes exits to provide continual feedback that powers several novel runtime monitoring and adaptation strategies. Apparate lowers median response latencies by 40.5--91.5% and 10.0--24.2% for diverse CV and NLP classification workloads, and median time-per-token latencies by 22.6--77.9% for generative scenarios, without affecting throughputs or violating tight accuracy constraints.

Linear attention has recently gained significant attention for long-context inference due to its constant decoding cost with respect to context length. However, existing serving systems typically serve linear attention by recurrently computing and updating a large linear attention state in every decoding step. Since the state is much larger than the per-token key and value, recurrent decoding incurs substantial memory access and becomes inefficient for serving linear attention. In this paper, we propose KVBuffer, an IO-aware serving mechanism for linear attention. By buffering recent keys and values, KVBuffer enables serving systems to compute linear attention outputs in more flexible and memory-efficient ways. For decoding, KVBuffer enables chunkwise computation, which reduces average memory access and decoding latency by deferring state updates and applying them in batch. For speculative decoding, KVBuffer verifies draft tokens in parallel and avoids storing temporary states. For short contexts, KVBuffer computes attention outputs directly from buffered keys and values, without creating or updating the linear attention state. We implement KVBuffer in SGLang for Qwen3-Next. Our evaluations show that KVBuffer can reduce linear attention decoding latency by up to 45.17% and increase the maximum number of serving requests by 5x for speculative decoding when verifying four draft tokens.

Large Language Model (LLM) serving faces a fundamental tension between stringent latency Service Level Objectives (SLOs) and limited GPU memory capacity. When high request rates exhaust the KV cache budget, existing LLM inference systems often suffer severe head-of-line (HOL) blocking. While prior work explored PCIe-based offloading, these approaches cannot sustain responsiveness under high request rates, often failing to meet tight Time-To-First-Token (TTFT) and Time-Between-Tokens (TBT) SLOs. We present SuperInfer, a high-performance LLM inference system designed for emerging Superchips (e.g., NVIDIA GH200) with tightly coupled GPU-CPU architecture via NVLink-C2C. SuperInfer introduces RotaSched, the first proactive, SLO-aware rotary scheduler that rotates requests to maintain responsiveness on Superchips, and DuplexKV, an optimized rotation engine that enables full-duplex transfer over NVLink-C2C. Evaluations on GH200 using various models and datasets show that SuperInfer improves TTFT SLO attainment rates by up to 74.7% while maintaining comparable TBT and throughput compared to state-of-the-art systems, demonstrating that SLO-aware scheduling and memory co-design unlocks the full potential of Superchips for responsive LLM serving.

Large Language Model (LLM) inference in production must meet stringent service-level objectives for both time-to-first-token (TTFT) and time-between-token (TBT) while maximizing throughput under fixed compute, memory, and interconnect budgets. Modern serving systems adopt stall-free scheduling techniques such as chunked prefill, which splits long prompt processing along the token dimension and interleaves prefill with ongoing decode iterations. While effective at stabilizing TBT, chunked prefill incurs substantial overhead in Mixture-of-Experts (MoE) models: redundant expert weight loads increase memory traffic by up to 39% and inflate energy consumption. We propose layered prefill, a new scheduling paradigm that treats transformer layer groups as the primary scheduling unit. By vertically partitioning the model into contiguous layer groups and interleaving prefill and decode across the groups, layered prefill sustains stall-free decoding while eliminating chunk-induced MoE weight reloads. It reduces off-chip bandwidth demand, lowering TTFT by up to 70%, End-to-End latency by 41% and per-token energy by up to 22%. Evaluations show that layered prefill consistently improves the TTFT--TBT Pareto frontier over chunked prefill, reducing expert-load traffic and energy cost while maintaining stall-free decoding. Overall, shifting the scheduling axis from tokens to layers unlocks a new operating regime for high-efficiency, energy-aware LLM serving in co-located environments.

Serverless computing has grown rapidly for serving Large Language Model (LLM) inference due to its pay-as-you-go pricing, fine-grained GPU usage, and rapid scaling. However, our analysis reveals that current serverless can effectively serve general LLM but fail with Low-Rank Adaptation (LoRA) inference due to three key limitations: 1) massive parameter redundancy among functions where 99% of weights are unnecessarily duplicated, 2) costly artifact loading latency beyond LLM loading, and 3) magnified resource contention when serving multiple LoRA LLMs. These inefficiencies lead to massive GPU wastage, increased Time-To-First-Token (TTFT), and high monetary costs. We propose ServerlessLoRA, a novel serverless inference system designed for faster and cheaper LoRA LLM serving. ServerlessLoRA enables secure backbone LLM sharing across isolated LoRA functions to reduce redundancy. We design a pre-loading method that pre-loads comprehensive LoRA artifacts to minimize cold-start latency. Furthermore, ServerlessLoRA employs contention aware batching and offloading to mitigate GPU resource conflicts during bursty workloads. Experiment on industrial workloads demonstrates that ServerlessLoRA reduces TTFT by up to 86% and cuts monetary costs by up to 89% compared to state-of-the-art LLM inference solutions.

Quantization is a widely-used compression technology to reduce the overhead of serving large language models (LLMs) on terminal devices and in cloud data centers. However, prevalent quantization methods, such as 8-bit weight-activation or 4-bit weight-only quantization, achieve limited performance improvements due to poor support for low-precision (e.g., 4-bit) activation. This work, for the first time, realizes practical W4A4KV4 serving for LLMs, fully utilizing the INT4 tensor cores on modern GPUs and reducing the memory bottleneck caused by the KV cache. Specifically, we propose a novel fine-grained mixed-precision quantization algorithm (FMPQ) that compresses most activations into 4-bit with negligible accuracy loss. To support mixed-precision matrix multiplication for W4A4 and W4A8, we develop a highly optimized W4Ax kernel. Our approach introduces a novel mixed-precision data layout to facilitate access and fast dequantization for activation and weight tensors, utilizing the GPU's software pipeline to hide the overhead of data loading and conversion. Additionally, we propose fine-grained streaming multiprocessor (SM) scheduling to achieve load balance across different SMs. We integrate the optimized W4Ax kernel into our inference framework, COMET, and provide efficient management to support popular LLMs such as LLaMA-3-70B. Extensive evaluations demonstrate that, when running LLaMA family models on a single A100-80G-SMX4, COMET achieves a kernel-level speedup of 2.88times over cuBLAS and a 2.02 times throughput improvement compared to TensorRT-LLM from an end-to-end framework perspective.

Mixture-of-Expert (MoE) based large language models (LLMs), such as the recent Mixtral and DeepSeek-MoE, have shown great promise in scaling model size without suffering from the quadratic growth of training cost of dense transformers. Like dense models, training MoEs requires answering the same question: given a training budget, what is the optimal allocation on the model size and number of tokens? We study the scaling law of MoE-based LLMs regarding the relations between the model performance, model size, dataset size, and the expert degree. Echoing previous research studying MoE in different contexts, we observe the diminishing return of increasing the number of experts, but this seems to suggest we should scale the number of experts until saturation, as the training cost would remain constant, which is problematic during inference time. We propose to amend the scaling law of MoE by introducing inference efficiency as another metric besides the validation loss. We find that MoEs with a few (4/8) experts are the most serving efficient solution under the same performance, but costs 2.5-3.5x more in training. On the other hand, training a (16/32) expert MoE much smaller (70-85%) than the loss-optimal solution, but with a larger training dataset is a promising setup under a training budget.

Large Language Models (LLMs) with hundreds of billions of parameters have transformed the field of machine learning. However, serving these models at inference time is both compute and memory intensive, where a single request can require multiple GPUs and tens of Gigabytes of memory. Multi-Head Attention is one of the key components of LLMs, which can account for over 50% of LLMs memory and compute requirement. We observe that there is a high amount of redundancy across heads on which tokens they pay attention to. Based on this insight, we propose Clustered Head Attention (CHAI). CHAI combines heads with a high amount of correlation for self-attention at runtime, thus reducing both memory and compute. In our experiments, we show that CHAI is able to reduce the memory requirements for storing K,V cache by up to 21.4% and inference time latency by up to 1.73x without any fine-tuning required. CHAI achieves this with a maximum 3.2% deviation in accuracy across 3 different models (i.e. OPT-66B, LLAMA-7B, LLAMA-33B) and 5 different evaluation datasets.

Multimodal large language models (MLLMs) extend LLMs to handle images, videos, and audio by incorporating feature extractors and projection modules. However, these additional components -- combined with complex inference pipelines and heterogeneous workloads -- introduce significant inference overhead. Therefore, efficiently serving MLLMs remains a major challenge. Current tightly coupled serving architectures struggle to distinguish between mixed request types or adapt parallelism strategies to different inference stages, leading to increased time-to-first-token (TTFT) latency and poor resource utilization. To address this, we introduce Elastic Multimodal Parallelism (EMP), a new serving paradigm that elastically adapts to resource heterogeneity across request types and inference stages. Building upon EMP, we develop ElasticMM, an MLLM serving system that (1) separates requests into independent modality groups with dynamic resource allocation via a modality-aware load balancer; (2) decouples inference stages and enables parallelism adjustment and adaptive scaling via elastic partition scheduling; and (3) improves inference efficiency through unified multimodal prefix caching and non-blocking encoding. Experiments on diverse real-world datasets show that ElasticMM outperforms state-of-the-art (SOTA) serving systems, reducing TTFT by up to 4.2x and achieving 3.2-4.5x higher throughput while meeting service-level objectives (SLOs).

The inference demand for LLMs has skyrocketed in recent months, and serving models with low latencies remains challenging due to the quadratic input length complexity of the attention layers. In this work, we investigate the effect of dropping MLP and attention layers at inference time on the performance of Llama-v2 models. We find that dropping dreeper attention layers only marginally decreases performance but leads to the best speedups alongside dropping entire layers. For example, removing 33\% of attention layers in a 13B Llama2 model results in a 1.8\% drop in average performance over the OpenLLM benchmark. We also observe that skipping layers except the latter layers reduces performances for more layers skipped, except for skipping the attention layers.

ModeSwitch-LLM is a lightweight request-boundary controller for improving single-GPU large language model inference efficiency by routing each request to an appropriate fixed inference mode. Instead of relying on one static serving configuration, the system selects among FP16, quantized modes, speculative decoding, and hybrid modes such as GPTQ plus prefix caching and INT8 plus continuous batching using cheap workload-level features. We evaluate ModeSwitch-LLM on Meta-Llama-3.1-8B-Instruct served on a single NVIDIA A100 GPU. On deployment-style synthetic workloads, the online controller achieves a 2.10x mean latency speedup over FP16 and a 0.48x mean energy ratio, corresponding to 51.7% lower energy per token. On automatic benchmarks used as a quality gate, accuracy remains close to FP16 with a mean delta of +0.17 percentage points. We also evaluate lightweight learned routers, but find that they do not clearly outperform the rule-based controller because they add routing overhead and more often select modes that violate quality, energy, or memory constraints. These results show that simple request-aware routing can recover substantial efficiency from existing inference modes without retraining the model or changing its architecture.

Speculative decoding can significantly accelerate LLM serving, yet most deployments today disentangle speculator training from serving, treating speculator training as a standalone offline modeling problem. We show that this decoupled formulation introduces substantial deployment and adaptation lag: (1) high time-to-serve, since a speculator must be trained offline for a considerable period before deployment; (2) delayed utility feedback, since the true end-to-end decoding speedup is only known after training and cannot be inferred reliably from acceptance rate alone due to model-architecture and system-level overheads; and (3) domain-drift degradation, as the target model is repurposed to new domains and the speculator becomes stale and less effective. To address these issues, we present Aurora, a unified training-serving system that closes the loop by continuously learning a speculator directly from live inference traces. Aurora reframes online speculator learning as an asynchronous reinforcement-learning problem: accepted tokens provide positive feedback, while rejected speculator proposals provide implicit negative feedback that we exploit to improve sample efficiency. Our design integrates an SGLang-based inference server with an asynchronous training server, enabling hot-swapped speculator updates without service interruption. Crucially, Aurora supports day-0 deployment: a speculator can be served immediately and rapidly adapted to live traffic, improving system performance while providing immediate utility feedback. Across experiments, Aurora achieves a 1.5x day-0 speedup on recently released frontier models (e.g., MiniMax M2.1 229B and Qwen3-Coder-Next 80B). Aurora also adapts effectively to distribution shifts in user traffic, delivering an additional 1.25x speedup over a well-trained but static speculator on widely used models (e.g., Qwen3 and Llama3).

Mixed-precision inference techniques reduce the memory and computational demands of Large Language Models (LLMs) by applying hybrid precision formats to model weights, activations, and KV caches. This work introduces mixed-precision LLM inference techniques that encompass (i) systematic memory and compute optimization across hierarchical storage and tensor core architectures, and (ii) comprehensive end-to-end mixed-precision optimization across diverse precision formats and hardware configurations. Our approach features two novel mixed-precision pipelines designed for optimal hardware utilization: a General Matrix Multiply (GEMM) pipeline that optimizes matrix operations through offline weight packing and online acceleration, and an attention pipeline that enables efficient attention computation with arbitrary Query, Key, and Value precision combinations. The key implementation of the pipelines includes (i) hardware-aware weight packing for automatic format optimization, (ii) adaptive head alignment for efficient attention computation, (iii) instruction-level parallelism for memory hierarchy exploitation, and (iv) KV memory loading pipeline for enhanced inference efficiency. We conduct comprehensive evaluations across 16 popular LLMs and 4 representative GPU architectures. Results demonstrate that our approach achieves up to 61% lower serving latency (30% on average) and up to 156% higher throughput (58% on average) in mixed-precision workloads compared to existing mixed-precision frameworks, establishing consistent performance improvements across all tested configurations and hardware types. This work is integrated into TurboMind, a high-performance inference engine of the LMDeploy project, which is open-sourced and publicly available at https://github.com/InternLM/lmdeploy.

Large Language Models (LLMs) demonstrate exceptional performance but entail significant memory and computational costs, restricting their practical deployment. While existing INT4/INT8 quantization reduces these costs, they often degrade accuracy or lack optimal efficiency. INT6 quantization offers a superior trade-off between model accuracy and inference efficiency, but lacks hardware support in modern GPUs, forcing emulation via higher-precision arithmetic units that limit acceleration. In this paper, we propose FlexQ, a novel post-training INT6 quantization framework combining algorithmic innovation with system-level optimizations. FlexQ employs uniform 6-bit weight quantization across all layers, with adaptive retention of 8-bit activations in layers identified through layer-wise sensitivity analysis. To maximize hardware efficiency, we develop a specialized high-performance GPU kernel supporting matrix multiplication for W6A6 and W6A8 representations via Binary Tensor Core (BTC) equivalents, effectively bypassing the lack of native INT6 tensor cores. Evaluations on LLaMA models show FlexQ maintains near-FP16 accuracy, with perplexity increases of no more than 0.05. The proposed kernel achieves an average 1.39times speedup over ABQ-LLM on LLaMA-2-70B linear layers. End-to-end, FlexQ delivers 1.33times inference acceleration and 1.21times memory savings over SmoothQuant. Code is released at https://github.com/FlyFoxPlayer/FlexQ.

Mixture of Experts (MoE) LLMs, characterized by their sparse activation patterns, offer a promising approach to scaling language models while avoiding proportionally increasing the inference cost. However, their large parameter sizes present deployment challenges in resource-constrained environments with limited GPU memory capacity, as GPU memory is often insufficient to accommodate the full set of model weights. Consequently, typical deployments rely on CPU-GPU hybrid execution: the GPU handles compute-intensive GEMM operations, while the CPU processes the relatively lightweight attention mechanism. This setup introduces a key challenge: how to effectively optimize resource utilization across CPU and GPU? Prior work has designed system optimizations based on performance models with limited scope. Specifically, such models do not capture the complex interactions between hardware properties and system execution mechanisms. Therefore, previous approaches neither identify nor achieve the hardware limit. This paper presents MoE-Lens, a high-throughput MoE LLM inference system designed through holistic performance modeling for resource-constrained environments. Our performance model thoroughly analyzes various fundamental system components, including CPU memory capacity, GPU compute power, and workload characteristics, to understand the theoretical performance upper bound of MoE inference. Furthermore, it captures the system execution mechanisms to identify the key hardware bottlenecks and accurately predict the achievable throughput. Informed by our performance model, MoE-Lens introduces an inference system approaching hardware limits. Evaluated on diverse MoE models and datasets, MoE-Lens outperforms the state-of-the-art solution by 4.6x on average (up to 25.5x), with our theoretical model predicting performance with an average 94% accuracy.

Large language models have demonstrated promising capabilities upon scaling up parameters. However, serving large language models incurs substantial computation and memory movement costs due to their large scale. Quantization methods have been employed to reduce service costs and latency. Nevertheless, outliers in activations hinder the development of INT4 weight-activation quantization. Existing approaches separate outliers and normal values into two matrices or migrate outliers from activations to weights, suffering from high latency or accuracy degradation. Based on observing activations from large language models, outliers can be classified into channel-wise and spike outliers. In this work, we propose Rotated Runtime Smooth (RRS), a plug-and-play activation smoother for quantization, consisting of Runtime Smooth and the Rotation operation. Runtime Smooth (RS) is introduced to eliminate channel-wise outliers by smoothing activations with channel-wise maximums during runtime. The rotation operation can narrow the gap between spike outliers and normal values, alleviating the effect of victims caused by channel-wise smoothing. The proposed method outperforms the state-of-the-art method in the LLaMA and Qwen families and improves WikiText-2 perplexity from 57.33 to 6.66 for INT4 inference.

Membership inference attacks aim to infer whether an individual record was used to train a model, serving as a key tool for disclosure auditing. While such evaluations are useful to demonstrate risk, they are computationally expensive and often make strong assumptions about potential adversaries' access to models and training environments, and thus do not provide very tight bounds on leakage from potential attacks. We show how prior claims around black-box access being sufficient for optimal membership inference do not hold for most useful settings such as stochastic gradient descent, and that optimal membership inference indeed requires white-box access. We validate our findings with a new white-box inference attack IHA (Inverse Hessian Attack) that explicitly uses model parameters by taking advantage of computing inverse-Hessian vector products. Our results show that both audits and adversaries may be able to benefit from access to model parameters, and we advocate for further research into white-box methods for membership privacy auditing.

Mixture of experts (MoE) is a popular technique to improve capacity of Large Language Models (LLMs) with conditionally-activated parallel experts. However, serving MoE models on memory-constrained devices is challenging due to the large parameter size. Typical solutions such as memory swapping or expert pruning may lead to significantly higher latency or severe accuracy loss. In this paper, we introduce SwapMoE, a framework for efficient serving of MoE-based large language models with tunable memory budgets. The main idea of SwapMoE is to keep a small dynamic set of important experts, namely Virtual Experts, in the main memory for inference, while seamlessly maintaining how the Virtual Experts map to the actual experts. Experiments have shown that SwapMoE can reduce the memory footprint while maintaining reasonable accuracy. For example, on text summarization tasks with Switch Transformer, SwapMoE can reduce the memory consumption from 14.2 GiB to 4.7 GiB, together with 50\% latency reduction and a slight Rouge-2 score drop of 0.041.

Quantization can accelerate large language model (LLM) inference. Going beyond INT8 quantization, the research community is actively exploring even lower precision, such as INT4. Nonetheless, state-of-the-art INT4 quantization techniques only accelerate low-batch, edge LLM inference, failing to deliver performance gains in large-batch, cloud-based LLM serving. We uncover a critical issue: existing INT4 quantization methods suffer from significant runtime overhead (20-90%) when dequantizing either weights or partial sums on GPUs. To address this challenge, we introduce QoQ, a W4A8KV4 quantization algorithm with 4-bit weight, 8-bit activation, and 4-bit KV cache. QoQ stands for quattuor-octo-quattuor, which represents 4-8-4 in Latin. QoQ is implemented by the QServe inference library that achieves measured speedup. The key insight driving QServe is that the efficiency of LLM serving on GPUs is critically influenced by operations on low-throughput CUDA cores. Building upon this insight, in QoQ algorithm, we introduce progressive quantization that can allow low dequantization overhead in W4A8 GEMM. Additionally, we develop SmoothAttention to effectively mitigate the accuracy degradation incurred by 4-bit KV quantization. In the QServe system, we perform compute-aware weight reordering and take advantage of register-level parallelism to reduce dequantization latency. We also make fused attention memory-bound, harnessing the performance gain brought by KV4 quantization. As a result, QServe improves the maximum achievable serving throughput of Llama-3-8B by 1.2x on A100, 1.4x on L40S; and Qwen1.5-72B by 2.4x on A100, 3.5x on L40S, compared to TensorRT-LLM. Remarkably, QServe on L40S GPU can achieve even higher throughput than TensorRT-LLM on A100. Thus, QServe effectively reduces the dollar cost of LLM serving by 3x. Code is available at https://github.com/mit-han-lab/qserve.

As Large Language Models (LLMs) have made significant advancements across various tasks, such as question answering, translation, text summarization, and dialogue systems, the need for accuracy in information becomes crucial, especially for serious financial products serving billions of users like Alipay. To address this, Alipay has developed a Retrieval-Augmented Generation (RAG) system that grounds LLMs on the most accurate and up-to-date information. However, for a real-world product serving millions of users, the inference speed of LLMs becomes a critical factor compared to a mere experimental model. Hence, this paper presents a generic framework for accelerating the inference process, resulting in a substantial increase in speed and cost reduction for our RAG system, with lossless generation accuracy. In the traditional inference process, each token is generated sequentially by the LLM, leading to a time consumption proportional to the number of generated tokens. To enhance this process, our framework, named lookahead, introduces a multi-branch strategy. Instead of generating a single token at a time, we propose a Trie-based Retrieval (TR) process that enables the generation of multiple branches simultaneously, each of which is a sequence of tokens. Subsequently, for each branch, a Verification and Accept (VA) process is performed to identify the longest correct sub-sequence as the final output. Our strategy offers two distinct advantages: (1) it guarantees absolute correctness of the output, avoiding any approximation algorithms, and (2) the worst-case performance of our approach is equivalent to the conventional process. We conduct extensive experiments to demonstrate the significant improvements achieved by applying our inference acceleration framework. Code is avaliable: https://github.com/alipay/PainlessInferenceAcceleration.

Security of model parameters and user data is critical for Transformer-based services, such as ChatGPT. While recent strides in secure two-party protocols have successfully addressed security concerns in serving Transformer models, their adoption is practically infeasible due to the prohibitive cryptographic overheads involved. Drawing insights from our hands-on experience in developing two real-world Transformer-based services, we identify the inherent efficiency bottleneck in the two-party assumption. To overcome this limitation, we propose a novel three-party threat model. Within this framework, we design a semi-symmetric permutation-based protection scheme and present STIP, the first secure Transformer inference protocol without any inference accuracy loss. Experiments on representative Transformer models in real systems show that STIP has practical security and outperforms state-of-the-art secure two-party protocols in efficiency by millions of times.

Transformer-based large Language Models (LLMs) become increasingly important in various domains. However, the quadratic time complexity of attention operation poses a significant challenge for scaling to longer contexts due to the extremely high inference latency and GPU memory consumption for caching key-value (KV) vectors. This paper proposes RetrievalAttention, a training-free approach to accelerate attention computation. To leverage the dynamic sparse property of attention, RetrievalAttention builds approximate nearest neighbor search (ANNS) indexes upon KV vectors in CPU memory and retrieves the most relevant ones via vector search during generation. Due to the out-of-distribution (OOD) between query vectors and key vectors, off-the-shelf ANNS indexes still need to scan O(N) (usually 30% of all keys) data for accurate retrieval, which fails to exploit the high sparsity. RetrievalAttention first identifies the OOD challenge of ANNS-based attention, and addresses it via an attention-aware vector search algorithm that can adapt to queries and only access 1--3% of data, thus achieving a sub-linear time complexity. RetrievalAttention greatly reduces the inference cost of long-context LLM with much lower GPU memory requirements while maintaining the model accuracy. Especially, RetrievalAttention only needs 16GB GPU memory for serving 128K tokens in LLMs with 8B parameters, which is capable of generating one token in 0.188 seconds on a single NVIDIA RTX4090 (24GB).

Deploying modern Speech Language Models (SpeechLMs) in streaming settings requires systems that provide low latency, high throughput, and strong guarantees of streamability. Existing systems fall short of supporting diverse models flexibly and efficiently. We present VoxServe, a unified serving system for SpeechLMs that optimizes streaming performance. VoxServe introduces a model-execution abstraction that decouples model architecture from system-level optimizations, thereby enabling support for diverse SpeechLM architectures within a single framework. Building on this abstraction, VoxServe implements streaming-aware scheduling and an asynchronous inference pipeline to improve end-to-end efficiency. Evaluations across multiple modern SpeechLMs show that VoxServe achieves 10-20x higher throughput than existing implementations at comparable latency while maintaining high streaming viability. The code of VoxServe is available at https://github.com/vox-serve/vox-serve.

Diffusion Large Language Models (dLLMs) have emerged as a promising alternative to Autoregressive Models (ARMs), utilizing parallel decoding to overcome sequential bottlenecks. However, existing research focuses primarily on kernel-level optimizations, lacking a holistic serving framework that addresses the unique memory dynamics of diffusion processes in production. We identify a critical "memory footprint crisis" specific to dLLMs, driven by monolithic logit tensors and the severe resource oscillation between compute-bound "Refresh" phases and bandwidth-bound "Reuse" phases. To bridge this gap, we present dLLM-Serve, an efficient dLLM serving system that co-optimizes memory footprint, computational scheduling, and generation quality. dLLM-Serve introduces Logit-Aware Activation Budgeting to decompose transient tensor peaks, a Phase-Multiplexed Scheduler to interleave heterogeneous request phases, and Head-Centric Sparse Attention to decouple logical sparsity from physical storage. We evaluate dLLM-Serve on diverse workloads (LiveBench, Burst, OSC) and GPUs (RTX 4090, L40S). Relative to the state-of-the-art baseline, dLLM-Serve improves throughput by 1.61times-1.81times on the consumer-grade RTX 4090 and 1.60times-1.74times on the server-grade NVIDIA L40S, while reducing tail latency by nearly 4times under heavy contention. dLLM-Serve establishes the first blueprint for scalable dLLM inference, converting theoretical algorithmic sparsity into tangible wall-clock acceleration across heterogeneous hardware.

Generating texts with a large language model (LLM) consumes massive amounts of memory. Apart from the already-large model parameters, the key/value (KV) cache that holds information about previous tokens in a sequence can grow to be even larger than the model itself. This problem is exacerbated in one of the current LLM serving frameworks which reserves the maximum sequence length of memory for the KV cache to guarantee generating a complete sequence as they do not know the output sequence length. This restricts us to use a smaller batch size leading to lower GPU utilization and above all, lower throughput. We argue that designing a system with a priori knowledge of the output sequence can mitigate this problem. To this end, we propose S^{3}, which predicts the output sequence length, schedules generation queries based on the prediction to increase device resource utilization and throughput, and handle mispredictions. Our proposed method achieves 6.49times throughput over those systems that assume the worst case for the output sequence length.

Large Vision-Language Models (LVLMs) enable sophisticated reasoning over images and videos, yet their inference is hindered by a systemic efficiency barrier known as visual token dominance. This overhead is driven by a multi-regime interplay between high-resolution feature extraction, quadratic attention scaling, and memory bandwidth constraints. We present a systematic taxonomy of efficiency techniques structured around the inference lifecycle, consisting of encoding, prefilling, and decoding. Unlike prior reviews focused on isolated optimizations, we analyze the end-to-end pipeline to reveal how upstream decisions dictate downstream bottlenecks, covering compute-bound visual encoding, the intensive prefilling of massive contexts, and the ''visual memory wall'' in bandwidth-bound decoding. By decoupling the efficiency landscape into the axes of shaping information density, managing long-context attention, and overcoming memory limits, this work provides a structured analysis of how isolated optimizations compose to navigate the trade-off between visual fidelity and system efficiency. The survey concludes by outlining four future frontiers supported by pilot empirical insights, including hybrid compression based on functional unit sensitivity, modality-aware decoding with relaxed verification, progressive state management for streaming continuity, and stage-disaggregated serving through hardware-algorithm co-design. Our literature repository is at https://github.com/SuDIS-ZJU/Efficient-LVLMs-Inference.

Mixture-of-Experts (MoE) model architecture has emerged as a promising solution for scaling transformer models efficiently, offering sparse activation that reduces computational costs while increasing model capacity. However, as MoE models scale, they need to be distributed across GPU devices, thus face critical performance bottlenecks due to their large memory footprint. Expert parallelism distributes experts across GPUs, however, faces key challenges including an unbalanced token routing and expert activation, resulting in communication tail latency and processing inefficiencies. While existing solutions address some of these issues, they fail to resolve the dual challenges of load imbalance and communication skew. The imbalance in token processing load across experts causes uneven processing times on different GPUs, while communication skew between GPUs leads to unbalanced inter-GPU data transfers. These factors degrade the performance of MoE models by increasing tail latency and reducing overall throughput. To address these limitations, we propose an Integer Linear Programming (ILP) formulation to optimize expert placement by jointly considering token load, communication, and computation costs. We exploit the property that there is a token routing dependency across layers, where tokens routed to a specific expert in one layer are likely to be routed to a limited set of experts in the subsequent layer. Our solution, MoETuner, offers an optimal expert-to-GPU assignment that minimizes inter-GPU token routing costs and balances token processing across devices, thereby reducing tail latency and end-to-end execution time. Experimental results demonstrate 9.3% and 17.5% of end-to-end speedups for single-node and multi-node inference respectively, showcasing the potential of our ILP-based optimization for offering expert parallel solutions for next-generation MoEs.

Large multimodal models (LMMs) demonstrate impressive capabilities in understanding images, videos, and audio beyond text. However, efficiently serving LMMs in production environments poses significant challenges due to their complex architectures and heterogeneous characteristics across their multi-stage inference pipelines. We present the first comprehensive systems analysis of two prominent LMM architectures, decoder-only and cross-attention, across six representative open-source models, revealing key systems design implications. We also present an in-depth analysis of production LMM inference traces, uncovering unique workload characteristics, including variable, heavy-tailed request distributions and bursty traffic patterns. Based on these insights, we propose ModServe, a modular LMM serving system that decouples stages for independent optimization and adaptive scaling. ModServe dynamically reconfigures stages and handles bursty traffic with modality-aware scheduling and autoscaling to meet tail latency SLOs while minimizing costs. ModServe achieves 3.3-5.5x higher throughput (leading to 25-41.3% cost saving) while meeting SLOs on a 128-GPU cluster with production traces.

Deep neural network (DNN) inference has become an important part of many data-center workloads. This has prompted focused efforts to design ever-faster deep learning accelerators such as GPUs and TPUs. However, an end-to-end DNN-based vision application contains more than just DNN inference, including input decompression, resizing, sampling, normalization, and data transfer. In this paper, we perform a thorough evaluation of computer vision inference requests performed on a throughput-optimized serving system. We quantify the performance impact of server overheads such as data movement, preprocessing, and message brokers between two DNNs producing outputs at different rates. Our empirical analysis encompasses many computer vision tasks including image classification, segmentation, detection, depth-estimation, and more complex processing pipelines with multiple DNNs. Our results consistently demonstrate that end-to-end application performance can easily be dominated by data processing and data movement functions (up to 56% of end-to-end latency in a medium-sized image, and sim 80% impact on system throughput in a large image), even though these functions have been conventionally overlooked in deep learning system design. Our work identifies important performance bottlenecks in different application scenarios, achieves 2.25times better throughput compared to prior work, and paves the way for more holistic deep learning system design.

Large language models (LLMs) have revolutionized natural language processing (NLP), yet open-source multilingual LLMs remain scarce, with existing models often limited in language coverage. Such models typically prioritize well-resourced languages, while widely spoken but under-resourced languages are often overlooked. To address this disparity, we introduce Babel, an open multilingual LLM that covers the top 25 languages by number of speakers, supports over 90% of the global population, and includes many languages neglected by other open multilingual LLMs. Unlike traditional continue pretraining approaches, Babel expands its parameter count through a layer extension technique that elevates Babel's performance ceiling. We introduce two variants: Babel-9B, designed for efficient inference and fine-tuning, and Babel-83B, which sets a new standard for open multilingual LLMs. Extensive evaluations on multilingual tasks demonstrate its superior performance compared to open LLMs of comparable size. In addition, using open-source supervised fine-tuning datasets, Babel achieves remarkable performance, with Babel-9B-Chat leading among 10B-sized LLMs and Babel-83B-Chat setting a new standard for multilingual tasks, reaching the same level of commercial models.

LLMs are widely adopted in production, pushing inference systems to their limits. Disaggregated LLM serving (e.g., PD separation and KV state disaggregation) improves scalability and cost efficiency, but it also turns KV into an explicit payload crossing network and storage boundaries, making KV a dominant end-to-end bottleneck. Existing KV compression are typically static runtime configurations, despite production service context varies over time in workload mix, bandwidth, and SLO/quality budgets. As a result, a fixed choice can be suboptimal or even increase latency. We present KVServe, the first service-aware and adaptive KV communication compression framework for disaggregated LLM serving: KVServe (1) unifies KV compression into a modular strategy space with new components and cross-method recomposition; (2) introduces Bayesian Profiling Engine that efficiently searches this space and distills a 3D Pareto candidate set, reducing 50times offline search overhead; and (3) deploys a Service-Aware Online Controller that combines an analytical latency model with a lightweight bandit to select profiles under constraints and correct offline-to-online mismatch. Integrated into vLLM and evaluated across datasets, models, GPUs and networks, KVServe achieves up to 9.13times JCT speedup in PD-separated serving and up to 32.8times TTFT reduction in KV-disaggregated serving.

It is now a common business practice to buy access to large language model (LLM) inference rather than self-host, because of significant upfront hardware infrastructure and energy costs. However, as a buyer, there is no mechanism to verify the authenticity of the advertised service including the serving hardware platform, e.g. that it is actually being served using an NVIDIA H100. Furthermore, there are reports suggesting that model providers may deliver models that differ slightly from the advertised ones, often to make them run on less expensive hardware. That way, a client pays premium for a capable model access on more expensive hardware, yet ends up being served by a (potentially less capable) cheaper model on cheaper hardware. In this paper we introduce \textbf{hardware and software platform inference (HSPI)} -- a method for identifying the underlying architecture and software stack of a (black-box) machine learning model solely based on its input-output behavior. Our method leverages the inherent differences of various architectures and compilers to distinguish between different types and software stacks. By analyzing the numerical patterns in the model's outputs, we propose a classification framework capable of accurately identifying the used for model inference as well as the underlying software configuration. Our findings demonstrate the feasibility of inferring type from black-box models. We evaluate HSPI against models served on different real hardware and find that in a white-box setting we can distinguish between different s with between 83.9% and 100% accuracy. Even in a black-box setting we are able to achieve results that are up to three times higher than random guess accuracy.

Large language model (LLM) serving has transformed from stateless to stateful systems, utilizing techniques like context caching and disaggregated inference. These optimizations extend the lifespan and domain of the KV cache, necessitating a new architectural approach. We present MemServe, a unified system that integrates both inter-request and intra-request optimizations. MemServe introduces MemPool, an elastic memory pool managing distributed memory and KV caches across serving instances. Using MemPool APIs, MemServe combines context caching with disaggregated inference for the first time, supported by a global scheduler that enhances cache reuse through a global prompt tree-based locality-aware policy. Tests show that MemServe significantly improves job completion time and time-to-first-time.

We introduce ISO-Bench, a benchmark for coding agents to test their capabilities on real-world inference optimization tasks. These tasks were taken from vLLM and SGLang, two of the most popular LLM serving frameworks. Each task provides an agent with a codebase and bottleneck description, whereby the agent must produce an optimization patch evaluated against expert human solutions. We curated 54 tasks from merged pull requests with measurable performance improvements. While existing benchmarks heavily use runtime-based metrics, such approaches can be gamed to pass tests without capturing the actual intent of the code changes. Therefore, we combine both hard (execution-based) and soft (LLM-based) metrics to show that both are necessary for complete evaluation. While evaluating both closed and open-source coding agents, we find no single agent dominates across codebases. Surprisingly, agents often identify correct bottlenecks but fail to execute working solutions. We also show that agents with identical underlying models differ substantially, suggesting scaffolding is as important as the model.

Large language models have been widely adopted across different tasks, but their auto-regressive generation nature often leads to inefficient resource utilization during inference. While batching is commonly used to increase throughput, performance gains plateau beyond a certain batch size, especially with smaller models, a phenomenon that existing literature typically explains as a shift to the compute-bound regime. In this paper, through an in-depth GPU-level analysis, we reveal that large-batch inference remains memory-bound, with most GPU compute capabilities underutilized due to DRAM bandwidth saturation as the primary bottleneck. To address this, we propose a Batching Configuration Advisor (BCA) that optimizes memory allocation, reducing GPU memory requirements with minimal impact on throughput. The freed memory and underutilized GPU compute capabilities can then be leveraged by concurrent workloads. Specifically, we use model replication to improve serving throughput and GPU utilization. Our findings challenge conventional assumptions about LLM inference, offering new insights and practical strategies for improving resource utilization, particularly for smaller language models.

Zeroth-order (ZO) fine-tuning is attractive for large language models because it replaces backpropagation with forward objective evaluations. Existing implementations nevertheless execute ZO algorithms inside conventional training loops, even though their dominant work is repeated scoring under nearby parameter states. This creates a workload-runtime mismatch: the algorithm asks for structured inference-style scoring, while the system exposes a sequence of fragmented training-loop steps. We show that LLM ZO fine-tuning is an inference-dominated workload and execute its repeated scoring phase through a serving runtime. On OPT-13B SST-2, the resulting vLLM execution path completes the 20k-step LoZO run in 0.51 estimated training hours versus 4.15 hours for the official LoZO baseline under the matched LoRA-only setting, an 8.13x speedup, while reaching 0.922 final evaluation accuracy and 0.931 final full-validation accuracy. In core-step scaling experiments across OPT-1.3B to OPT-13B, the same runtime reorganization gives 2.34x--7.72x speedups. A MeZO-style high-rank factorized experiment shows that the same runtime paradigm can track a MeZO-like loss trajectory while running up to 2.55x faster. More broadly, representing ZO updates as dynamic adapter states suggests a practical path toward inference-time training, where lightweight adaptation can be scheduled as an inference-like workload rather than as a separate training job.

The large size of the KV cache has become a major bottleneck for serving LLMs with increasing context lengths. In response, many KV cache compression methods, such as token dropping and quantization, have been proposed. However, almost all of these methods are inherently lossy-despite minimal accuracy degradation for short outputs, their outputs increasingly diverge from full-KV-cache outputs as more tokens are decoded, which leads to catastrophic failures in code generation and tool calling. We present VeriCache, the first inference framework that ensures the same output as full-KV-cache decoding but largely preserves the high decoding throughput of a range of KV cache compression algorithms. VeriCache uses the compressed KV cache to draft tokens, then verifies them against the full KV cache. While it may seem like just speculative decoding, VeriCache requires addressing a key system challenge to work-keeping the full KV cache out of GPU memory and minimizing the overhead of swapping it in for verification. The insight is two-fold: (1) compressed-KV decoding can be parallelized with full-KV swap, because one is HBM-bandwidth-bound and the other is PCIe/network-bound, and (2) the compressed KV cache often produces output similar to the full KV cache, allowing a long drafting horizon to amortize each full-KV swap. VeriCache applies to both long-context decoding and remote prefix caching, supports a broad family of token-dropping and quantization methods through a uniform compressor interface, and composes with traditional speculative decoding. Experimental results show that VeriCache achieves up to 4X higher throughput than full-KV inference while producing identical outputs.

Mixture-of-Experts (MoE) models typically fix the number of activated experts k at both training and inference. However, real-world deployments often face heterogeneous hardware, fluctuating workloads, and diverse quality-latency requirements, while training separate models for each scenario is costly. Considering that MoE models already operate with sparse activation, adjusting the number of activated experts offers a natural path to serving diverse budgets with a single model. Yet, we find that activating more experts k' (> k) at inference does not yield the expected gains. Instead, performance degrades rapidly after only a slight increase, a phenomenon we term the inference-time scaling wall. Further investigation reveals that this degradation stems from a lack of learned collaboration among experts. To address this, we introduce Elastic Mixture-of-Experts (EMoE), a novel training framework that enables MoE models to elastically vary the number of activated experts at inference. By simultaneously training experts to collaborate in diverse combinations and encouraging the router to make high-quality selections, EMoE ensures robust performance across inference budgets. Extensive experiments across four MoE architectures (7B--21B) and nine benchmarks show that EMoE significantly expands the effective scaling range to 2-3times the training-time k, while also achieving higher peak performance.

Transformer-based large models excel in natural language processing and computer vision, but face severe computational inefficiencies due to the self-attention's quadratic complexity with input tokens. Recently, researchers have proposed a series of methods based on block selection and compression to alleviate this problem, but they either have issues with semantic incompleteness or poor training-inference efficiency. To comprehensively address these challenges, we propose ChunkLLM, a lightweight and pluggable training framework. Specifically, we introduce two components: QK Adapter (Q-Adapter and K-Adapter) and Chunk Adapter. The former is attached to each Transformer layer, serving dual purposes of feature compression and chunk attention acquisition. The latter operates at the bottommost layer of the model, functioning to detect chunk boundaries by leveraging contextual semantic information. During the training phase, the parameters of the backbone remain frozen, with only the QK Adapter and Chunk Adapter undergoing training. Notably, we design an attention distillation method for training the QK Adapter, which enhances the recall rate of key chunks. During the inference phase, chunk selection is triggered exclusively when the current token is detected as a chunk boundary, thereby accelerating model inference. Experimental evaluations are conducted on a diverse set of long-text and short-text benchmark datasets spanning multiple tasks. ChunkLLM not only attains comparable performance on short-text benchmarks but also maintains 98.64% of the performance on long-context benchmarks while preserving a 48.58% key-value cache retention rate. Particularly, ChunkLLM attains a maximum speedup of 4.48x in comparison to the vanilla Transformer in the processing of 120K long texts.

The mixture of experts (MoE) model is a sparse variant of large language models (LLMs), designed to hold a better balance between intelligent capability and computational overhead. Despite its benefits, MoE is still too expensive to deploy on resource-constrained edge devices, especially with the demands of on-device inference services. Recent research efforts often apply model compression techniques, such as quantization, pruning and merging, to restrict MoE complexity. Unfortunately, due to their predefined static model optimization strategies, they cannot always achieve the desired quality-overhead trade-off when handling multiple requests, finally degrading the on-device quality of service. These limitations motivate us to propose the D^2MoE, an algorithm-system co-design framework that matches diverse task requirements by dynamically allocating the most proper bit-width to each expert. Specifically, inspired by the nested structure of matryoshka dolls, we propose the matryoshka weight quantization (MWQ) to progressively compress expert weights in a bit-nested manner and reduce the required runtime memory. On top of it, we further optimize the I/O-computation pipeline and design a heuristic scheduling algorithm following our hottest-expert-bit-first (HEBF) principle, which maximizes the expert parallelism between I/O and computation queue under constrained memory budgets, thus significantly reducing the idle temporal bubbles waiting for the experts to load. Evaluations on real edge devices show that D^2MoE improves the overall inference throughput by up to 1.39times and reduces the peak memory footprint by up to 53% over the latest on-device inference frameworks, while still preserving comparable serving accuracy as its INT8 counterparts.

Large Language Models (LLMs) have gained immense success in revolutionizing various applications, including content generation, search and recommendation, and AI-assisted operation. To reduce high training costs, Mixture-of-Experts (MoE) architecture has become a popular backbone for modern LLMs. However, despite the benefits, serving MoE-based LLMs experience severe memory inefficiency due to sparsely activated experts. Recent studies propose to offload inactive experts from GPU memory to CPU memory to improve the serving efficiency of MoE models. However, they either incur high inference latency or high model memory footprints due to coarse-grained designs. To tame the latency-memory trade-off in MoE serving, we present fMoE, a fine-grained expert offloading system for MoE serving that achieves low inference latency with memory efficiency. We design fMoE to extract fine-grained expert selection patterns from MoE models and semantic hints from input prompts to efficiently guide expert prefetching, caching, and offloading decisions. fMoE is prototyped on top of HuggingFace Transformers and deployed on a six-GPU testbed. Experiments with open-source MoE models and real-world workloads show that fMoE reduces inference latency by 47% and improves expert hit rate by 36% over state-of-the-art solutions.

Large language models (LLMs) have shown remarkable performance across a wide range of applications, often outperforming human experts. However, deploying these parameter-heavy models efficiently for diverse inference use cases requires carefully designed hardware platforms with ample computing, memory, and network resources. With LLM deployment scenarios and models evolving at breakneck speed, the hardware requirements to meet SLOs remains an open research question. In this work, we present an analytical tool, GenZ, to study the relationship between LLM inference performance and various platform design parameters. Our analysis provides insights into configuring platforms for different LLM workloads and use cases. We quantify the platform requirements to support SOTA LLMs models like LLaMA and GPT-4 under diverse serving settings. Furthermore, we project the hardware capabilities needed to enable future LLMs potentially exceeding hundreds of trillions of parameters. The trends and insights derived from GenZ can guide AI engineers deploying LLMs as well as computer architects designing next-generation hardware accelerators and platforms. Ultimately, this work sheds light on the platform design considerations for unlocking the full potential of large language models across a spectrum of applications. The source code is available at https://github.com/abhibambhaniya/GenZ-LLM-Analyzer .

Lossless model compression holds tremendous promise for alleviating the memory and bandwidth bottlenecks in bit-exact Large Language Model (LLM) serving. However, existing approaches often result in substantial inference slowdowns due to fundamental design mismatches with GPU architectures: at the kernel level, variable-length bitstreams produced by traditional entropy codecs break SIMT parallelism; at the system level, decoupled pipelines lead to redundant memory traffic. We present ZipServ, a lossless compression framework co-designed for efficient LLM inference. ZipServ introduces Tensor-Core-Aware Triple Bitmap Encoding (TCA-TBE), a novel fixed-length format that enables constant-time, parallel decoding, together with a fused decompression-GEMM (ZipGEMM) kernel that decompresses weights on-the-fly directly into Tensor Core registers. This "load-compressed, compute-decompressed" design eliminates intermediate buffers and maximizes compute intensity. Experiments show that ZipServ reduces the model size by up to 30%, achieves up to 2.21x kernel-level speedup over NVIDIA's cuBLAS, and expedites end-to-end inference by an average of 1.22x over vLLM. ZipServ is the first lossless compression system that provides both storage savings and substantial acceleration for LLM inference on GPUs.

The increasing usage of Large Language Models (LLMs) has resulted in a surging demand for planet-scale serving systems, where tens of thousands of GPUs continuously serve hundreds of millions of users. Consequently, throughput (under reasonable latency constraints) has emerged as a key metric that determines serving systems' performance. To boost throughput, various methods of inter-device parallelism (e.g., data, tensor, pipeline) have been explored. However, existing methods do not consider overlapping the utilization of different resources within a single device, leading to underutilization and sub-optimal performance. We propose NanoFlow, a novel serving framework that exploits intra-device parallelism, which overlaps the usage of resources including compute, memory, and network within a single device through operation co-scheduling. To exploit intra-device parallelism, NanoFlow introduces two key innovations: First, NanoFlow splits requests into nano-batches at the granularity of operations, which breaks the dependency of sequential operations in LLM inference and enables overlapping; then, to get benefit from overlapping, NanoFlow uses an operation-level pipeline with execution unit scheduling, which partitions the device's functional units and simultaneously executes different operations in each unit. NanoFlow automates the pipeline setup using a parameter search algorithm, which enables easily porting NanoFlow to different models. We implement NanoFlow on NVIDIA GPUs and evaluate end-to-end serving throughput on several popular models such as LLaMA-2-70B, Mixtral 8x7B, LLaMA-3-8B, etc.. With practical workloads, NanoFlow provides 1.91x throughput boost compared to state-of-the-art serving systems achieving 59% to 72% of optimal throughput across ported models.

The deployment and scaling of large language models (LLMs) have become critical as they permeate various applications, demanding high-throughput and low-latency serving systems. Existing frameworks struggle to balance these requirements, especially for workloads with long prompts. This paper introduces DeepSpeed-FastGen, a system that employs Dynamic SplitFuse, a novel prompt and generation composition strategy, to deliver up to 2.3x higher effective throughput, 2x lower latency on average, and up to 3.7x lower (token-level) tail latency, compared to state-of-the-art systems like vLLM. We leverage a synergistic combination of DeepSpeed-MII and DeepSpeed-Inference to provide an efficient and easy-to-use serving system for LLMs. DeepSpeed-FastGen's advanced implementation supports a range of models and offers both non-persistent and persistent deployment options, catering to diverse user scenarios from interactive sessions to long-running applications. We present a detailed benchmarking methodology, analyze the performance through latency-throughput curves, and investigate scalability via load balancing. Our evaluations demonstrate substantial improvements in throughput and latency across various models and hardware configurations. We discuss our roadmap for future enhancements, including broader model support and new hardware backends. The DeepSpeed-FastGen code is readily available for community engagement and contribution.

Large Language Models have revolutionized natural language processing, yet serving them efficiently in data centers remains challenging due to mixed workloads comprising latency-sensitive (LS) and best-effort (BE) jobs. Existing inference systems employ iteration-level first-come-first-served scheduling, causing head-of-line blocking when BE jobs delay LS jobs. We introduce QLLM, a novel inference system designed for Mixture of Experts (MoE) models, featuring a fine-grained, priority-aware preemptive scheduler. QLLM enables expert-level preemption, deferring BE job execution while minimizing LS time-to-first-token (TTFT). Our approach removes iteration-level scheduling constraints, enabling the scheduler to preempt jobs at any layer based on priority. Evaluations on an Nvidia A100 GPU show that QLLM significantly improves performance. It reduces LS TTFT by an average of 65.5times and meets the SLO at up to 7 requests/sec, whereas the baseline fails to do so under the tested workload. Additionally, it cuts LS turnaround time by up to 12.8times without impacting throughput. QLLM is modular, extensible, and seamlessly integrates with HF Mirror MoE models.

MoE (Mixture of Experts) prevails as a neural architecture that can scale modern transformer-based LLMs (Large Language Models) to unprecedented scales. Nevertheless, large MoEs' great demands of computing power, memory capacity and memory bandwidth make scalable serving a fundamental challenge and efficient parallel inference has become a requisite to attain adequate throughput under latency constraints. DeepSpeed-MoE, one state-of-the-art MoE inference framework, adopts a 3D-parallel paradigm including EP (Expert Parallelism), TP (Tensor Parallel) and DP (Data Parallelism). However, our analysis shows DeepSpeed-MoE's inference efficiency is largely bottlenecked by EP, which is implemented with costly all-to-all collectives to route token activation. Our work aims to boost DeepSpeed-MoE by strategically reducing EP's communication overhead with a technique named Speculative MoE. Speculative MoE has two speculative parallelization schemes, speculative token shuffling and speculative expert grouping, which predict outstanding tokens' expert routing paths and pre-schedule tokens and experts across devices to losslessly trim EP's communication volume. Besides DeepSpeed-MoE, we also build Speculative MoE into a prevailing MoE inference engine SGLang. Experiments show Speculative MoE can significantly boost state-of-the-art MoE inference frameworks on fast homogeneous and slow heterogeneous interconnects.

As inference on Large Language Models (LLMs) emerges as an important workload in machine learning applications, weight quantization has become a standard technique for efficient GPU deployment. Quantization not only reduces model size, but has also been shown to yield substantial speedups for single-user inference, due to reduced memory movement, with low accuracy impact. Yet, it remains open whether speedups are achievable also in batched settings with multiple parallel clients, which are highly relevant for practical serving. It is unclear whether GPU kernels can be designed to remain practically memory-bound, while supporting the substantially increased compute requirements of batched workloads. This paper resolves this question positively by describing the design of Mixed-precision Auto-Regressive LINear kernels, called MARLIN. Concretely, given a model whose weights are compressed via quantization to, e.g., 4 bits per element, MARLIN shows that batchsizes up to 16-32 can be supported with close to maximum (4times) quantization speedup, and larger batchsizes up to 64-128 with gradually decreasing, but still significant, acceleration. MARLIN accomplishes this via a combination of techniques, such as asynchronous memory access, complex task scheduling and pipelining, and bespoke quantization support. Our experiments show that MARLIN's near-optimal performance on individual LLM layers across different scenarios can also lead to end-to-end LLM inference speedups (of up to 2.8times) when integrated with the popular vLLM serving engine. Finally, MARLIN is extensible to further compression techniques, like NVIDIA 2:4 sparsity, leading to additional speedups.

Batch inference for agentic workloads stresses the GPU key-value (KV) cache in a sustained and cumulative manner, often causing severe throughput degradation well before memory capacity is exhausted. We identify this phenomenon as middle-phase thrashing, a previously under-characterized pathology in which cache efficiency collapses as long-lived agents accumulate state over time. We argue that mitigating this pathology requires moving beyond reactive, request-level cache management to proactive, agent-level admission control. Drawing inspiration from congestion control in distributed systems, we view the KV cache as a shared resource whose efficient utilization depends on feedback-driven regulation. Based on this insight, we present CONCUR, a lightweight control layer that regulates agent admission to bound aggregate cache pressure while preserving execution continuity. CONCUR adapts a cache-aware control algorithm to dynamically adjust the number of active agents using runtime cache signals. Across large models and real-world agent workloads, CONCUR prevents middle-phase thrashing and improves batch inference throughput by up to 4.09x on Qwen3-32B and 1.9x on DeepSeek-V3, while remaining compatible with existing LLM serving systems.

Observational studies require adjustment for confounding factors that are correlated with both the treatment and outcome. In the setting where the observed variables are tabular quantities such as average income in a neighborhood, tools have been developed for addressing such confounding. However, in many parts of the developing world, features about local communities may be scarce. In this context, satellite imagery can play an important role, serving as a proxy for the confounding variables otherwise unobserved. In this paper, we study confounder adjustment in this non-tabular setting, where patterns or objects found in satellite images contribute to the confounder bias. Using the evaluation of anti-poverty aid programs in Africa as our running example, we formalize the challenge of performing causal adjustment with such unstructured data -- what conditions are sufficient to identify causal effects, how to perform estimation, and how to quantify the ways in which certain aspects of the unstructured image object are most predictive of the treatment decision. Via simulation, we also explore the sensitivity of satellite image-based observational inference to image resolution and to misspecification of the image-associated confounder. Finally, we apply these tools in estimating the effect of anti-poverty interventions in African communities from satellite imagery.

Sparse Mixture-of-Experts (MoE) has been a successful approach for scaling multilingual translation models to billions of parameters without a proportional increase in training computation. However, MoE models are prohibitively large and practitioners often resort to methods such as distillation for serving. In this work, we investigate routing strategies at different granularity (token, sentence, task) in MoE models to bypass distillation. Experiments on WMT and a web-scale dataset suggest that task-level routing (task-MoE) enables us to extract smaller, ready-to-deploy sub-networks from large sparse models. On WMT, our task-MoE with 32 experts (533M parameters) outperforms the best performing token-level MoE model (token-MoE) by +1.0 BLEU on average across 30 language pairs. The peak inference throughput is also improved by a factor of 1.9x when we route by tasks instead of tokens. While distilling a token-MoE to a smaller dense model preserves only 32% of the BLEU gains, our sub-network task-MoE, by design, preserves all the gains with the same inference cost as the distilled student model. Finally, when scaling up to 200 language pairs, our 128-expert task-MoE (13B parameters) performs competitively with a token-level counterpart, while improving the peak inference throughput by a factor of 2.6x.

With the widespread deployment of long-context large language models (LLMs), there has been a growing demand for efficient support of high-throughput inference. However, as the key-value (KV) cache expands with the sequence length, the increasing memory footprint and the need to access it for each token generation both result in low throughput when serving long-context LLMs. While various dynamic sparse attention methods have been proposed to speed up inference while maintaining generation quality, they either fail to sufficiently reduce GPU memory consumption or introduce significant decoding latency by offloading the KV cache to the CPU. We present ShadowKV, a high-throughput long-context LLM inference system that stores the low-rank key cache and offloads the value cache to reduce the memory footprint for larger batch sizes and longer sequences. To minimize decoding latency, ShadowKV employs an accurate KV selection strategy that reconstructs minimal sparse KV pairs on-the-fly. By evaluating ShadowKV on a broad range of benchmarks, including RULER, LongBench, and Needle In A Haystack, and models like Llama-3.1-8B, Llama-3-8B-1M, GLM-4-9B-1M, Yi-9B-200K, Phi-3-Mini-128K, and Qwen2-7B-128K, we demonstrate that it can support up to 6times larger batch sizes and boost throughput by up to 3.04times on an A100 GPU without sacrificing accuracy, even surpassing the performance achievable with infinite batch size under the assumption of infinite GPU memory. The code is available at https://github.com/bytedance/ShadowKV.

Physical AI systems, including robots, autonomous vehicles, embodied agents and edge copilots, often run a different inference workload from cloud LLM serving: single-stream, batch-1 autoregressive decode, where one robot, camera feed or user session waits on the next token. This workload is usually described as memory-bandwidth-bound. Each decode step streams model weights and the active KV cache, so latency should scale with peak HBM bandwidth. We show that this account is true but incomplete. We measure batch-1 decode for three 7 to 8B-class GQA transformers across four NVIDIA GPUs: H100 SXM5, A100-80GB SXM4, L40S and L4. We evaluate context lengths from 2048 to 16384, producing 44 valid cells under a controlled bf16 SDPA setup. The achieved fraction of peak HBM bandwidth falls as peak bandwidth rises. On the headline Qwen-2.5-7B ctx=2048 cell, an L4 reaches roughly 81 percent of its analytic memory floor, while an H100 reaches only 27 percent. Physical-AI decode is memory-dominated, but faster memory does not translate into proportional latency gains. We test the missing term with a CUDA Graphs A/B experiment. On H100 at ctx=2048, CUDA Graphs improves decode latency by 1.259x across N=10 fresh sessions, with a 95 percent bootstrap confidence interval of 1.253 to 1.267. On L4, the same intervention gives only 1.028x. This isolates a launch-side overhead that becomes visible on fast GPUs but remains mostly hidden on slower, bandwidth-bound GPUs. The deployment implication is that memory savings matter only when the runtime realises them. On L4, bf16 decode sits close to the memory floor, but common quantised paths do not recover the expected 4x weight-traffic reduction: bnb-nf4 reaches 59.36 ms/step and AutoAWQ+Marlin reaches 45.24 ms/step from a 62.32 ms bf16 baseline. GPTQ+ExLlamaV2, with Ada-tuned int4 kernels, reaches 17.36 ms/step.

The increasing context window size in large language models (LLMs) has improved their ability to handle complex, long-text tasks. However, as the conversation rounds continue, it is required to store a large amount of KV cache in GPU memory, which significantly affects the efficiency and even availability of the model serving systems. This paper analyzes dialogue data from real users and discovers that the LLM inference manifests a watershed layer, after which the distribution of round-level attention shows notable similarity. We propose Round Attention, a novel round-level attention mechanism that only recalls and computes the KV cache of the most relevant rounds. The experiments show that our method saves 55\% memory usage without compromising model performance.

The key-value (KV) cache is a foundational optimization in Transformer-based large language models (LLMs), eliminating redundant recomputation of past token representations during autoregressive generation. However, its memory footprint scales linearly with context length, imposing critical bottlenecks on GPU memory capacity, memory bandwidth, and inference throughput as production LLMs push context windows from thousands to millions of tokens. Efficient KV cache management has thus become a first-order challenge for scalable LLM deployment. This paper provides a systematic review of recent KV cache optimization techniques, organizing them into five principal directions: cache eviction, cache compression, hybrid memory solutions, novel attention mechanisms, and combination strategies. For each category we analyze the underlying mechanisms, deployment trade-offs, and empirical performance across memory reduction, throughput, and model accuracy metrics. We further map techniques to seven practical deployment scenarios, including long-context single requests, high-throughput datacenter serving, edge devices, multi-turn conversations, and accuracy-critical reasoning, providing actionable guidance for practitioners selecting among competing approaches. Our analysis reveals that no single technique dominates across all settings; instead, the optimal strategy depends on context length, hardware constraints, and workload characteristics, pointing toward adaptive, multi-stage optimization pipelines as a promising direction for future research.

Attention efficiency is critical to large language model (LLM) inference. While prior advances optimize attention execution for individual requests (e.g., FlashAttention), production LLM serving relies on batching requests with highly heterogeneous sequence lengths for high serving throughput. This mismatch induces severe computation and I/O imbalance, exacerbates stragglers, and underutilizes GPU resources. We present PackInfer, a kernel-level attention framework that enables compute- and I/O-aware execution for heterogeneous batched inference. PackInfer orchestrates batched requests into load-balanced execution groups, effectively saturating GPU utilization by packing multiple requests into unified kernel launches. By constructing attention kernels directly over packed query-key regions, PackInfer eliminates redundant computation and balances thread-block execution. It then incorporates I/O-aware grouping that co-locates shared-prefix requests and reorganizes KV caches into group-contiguous layouts, reducing memory fragmentation and redundant data movement as generation evolves. Evaluations on real-world workloads show that PackInfer reduces inference latency by 13.0-20.1%, and improves throughput by 20% compared to the state-of-the-art FlashAttention.

Low-Rank Adaptation (LoRA) has become a widely adopted parameter-efficient fine-tuning (PEFT) technique for adapting large language models (LLMs) to downstream tasks. While prior work has explored strategies for integrating LLM training and serving, there still remains a gap in unifying fine-tuning and inference for LoRA-based models. We present Loquetier, a virtualized multi-LoRA framework that seamlessly integrates LoRA fine-tuning and serving within a single runtime. Loquetier introduces two key components: (1) a Virtualized Module that isolates PEFT-based modifications and supports multiple adapters on a shared base model, and (2) an optimized computation flow with a kernel design that merges fine-tuning and inference paths in forward propagation, enabling efficient batching and minimizing kernel invocation overhead. Extensive experiments across three task settings show that Loquetier consistently outperforms existing baselines in both performance and flexibility, achieving up to 3.0times the throughput of the state-of-the-art co-serving system on inference-only tasks and 46.4times higher SLO attainment than PEFT on unified fine-tuning and inference tasks. The implementation of Loquetier is publicly available at https://github.com/NJUDeepEngine/Loquetier.

The rise of LLMs has driven demand for private serverless deployments, characterized by moderate-scale models and infrequent requests. While existing solutions follow exclusive GPU deployment, we take a step back to explore modern platforms and find that: Emerging CPU architectures with built-in accelerators are capable of serving LLMs but remain underutilized, and both CPUs and GPUs can accommodate multiple LLMs simultaneously. We propose LLM-Mesh, a serverless inference scheme for small-to-mid-sized LLMs that enables elastic sharing across heterogeneous hardware. LLM-Mesh tackles three fundamental challenges: (1) precise, fine-grained compute resource allocation at token-level to handle fluctuating computational demands; (2) a coordinated and forward-looking memory scaling mechanism to detect out-of-memory hazards and reduce operational overhead; and (3) a dual approach that reduces resource fragmentation through proactive preemption and reactive bin-packing. Experimental results on 4 32-core CPUs and 4 A100 GPUs show that LLM-Meshimproves service capacity by 44% - 63% through sharing, while further leveraging CPUs boosts this to 91% - 159%.

Recent advances leverage post-training to enhance model reasoning performance, which typically requires costly training pipelines and still suffers from inefficient, overly lengthy outputs. We introduce Speculative Thinking, a training-free framework that enables large reasoning models to guide smaller ones during inference at the reasoning level, distinct from speculative decoding, which operates at the token level. Our approach is based on two observations: (1) reasoning-supportive tokens such as "wait" frequently appear after structural delimiters like "\n\n", serving as signals for reflection or continuation; and (2) larger models exhibit stronger control over reflective behavior, reducing unnecessary backtracking while improving reasoning quality. By strategically delegating reflective steps to a more capable model, our method significantly boosts the reasoning accuracy of reasoning models while shortening their output. With the assistance of the 32B reasoning model, the 1.5B model's accuracy on MATH500 increases from 83.2% to 89.4%, marking a substantial improvement of 6.2%. Simultaneously, the average output length is reduced from 5439 tokens to 4583 tokens, representing a 15.7% decrease. Moreover, when applied to a non-reasoning model (Qwen-2.5-7B-Instruct), our framework boosts its accuracy from 74.0% to 81.8% on the same benchmark, achieving a relative improvement of 7.8%.

The introduction of 8-bit floating-point (FP8) computation units in modern AI accelerators has generated significant interest in FP8-based large language model (LLM) inference. Unlike 16-bit floating-point formats, FP8 in deep learning requires a shared scaling factor. Additionally, while E4M3 and E5M2 are well-defined at the individual value level, their scaling and accumulation methods remain unspecified and vary across hardware and software implementations. As a result, FP8 behaves more like a quantization format than a standard numeric representation. In this work, we provide the first comprehensive analysis of FP8 computation and acceleration on two AI accelerators: the NVIDIA H100 and Intel Gaudi 2. Our findings highlight that the Gaudi 2, by leveraging FP8, achieves higher throughput-to-power efficiency during LLM inference, offering valuable insights into the practical implications of FP8 adoption for datacenter-scale LLM serving.

Large deep learning models have achieved impressive performance across a range of applications. However, their large memory requirements, including parameter memory and activation memory, have become a significant challenge for their practical serving. While existing methods mainly address parameter memory, the importance of activation memory has been overlooked. Especially for long input sequences, activation memory is expected to experience a significant exponential growth as the length of sequences increases. In this approach, we propose AutoChunk, an automatic and adaptive compiler system that efficiently reduces activation memory for long sequence inference by chunk strategies. The proposed system generates chunk plans by optimizing through multiple stages. In each stage, the chunk search pass explores all possible chunk candidates and the chunk selection pass identifies the optimal one. At runtime, AutoChunk employs code generation to automatically apply chunk strategies. The experiments demonstrate that AutoChunk can reduce over 80\% of activation memory while maintaining speed loss within 10%, extend max sequence length by 3.2x to 11.7x, and outperform state-of-the-art methods by a large margin.

Large language models(LLMs) are now used to power complex multi-turn agentic workflows. Existing systems run agentic inference by loosely assembling isolated components: an LLM inference engine (e.g., vLLM) and a tool orchestrator (e.g., Kubernetes). Although agentic workflows involve multiple LLM and tool requests, these systems schedule and allocate resources separately on a per-request basis, without end-to-end knowledge of the workflow. This leads to sub-optimal management of KV cache and tool execution environments. To address the challenges, we propose ThunderAgent, a fast, simple, and program-aware agentic inference system. We first abstract agentic workflows as LLM Programs, enabling a unified view of heterogeneous resources, including KV caches, system states, and external tool assets such as disk memory and network ports. Built upon this abstraction, ThunderAgent introduces a program-aware scheduler and a tool resource manager designed to maximize KV cache hit rates, mitigate memory imbalances, and enable asynchronous environment preparation. Evaluations across coding, routing, and scientific discovery agents demonstrate that ThunderAgent achieves 1.5-3.6x throughput improvements in serving, 1.8-3.9x in RL rollout, and up to 4.2x disk memory savings compared to state-of-the-art inference systems. To facilitate reproducibility and support future development, we open-source the system implementations of the whole ThunderAgent at: https://github.com/Agentic-Kinetics/ThunderAgent.

We introduce AIBrix, a cloud-native, open-source framework designed to optimize and simplify large-scale LLM deployment in cloud environments. Unlike traditional cloud-native stacks, AIBrix follows a co-design philosophy, ensuring every layer of the infrastructure is purpose-built for seamless integration with inference engines like vLLM. AIBrix introduces several key innovations to reduce inference costs and enhance performance including high-density LoRA management for dynamic adapter scheduling, LLM-specific autoscalers, and prefix-aware, load-aware routing. To further improve efficiency, AIBrix incorporates a distributed KV cache, boosting token reuse across nodes, leading to a 50% increase in throughput and a 70% reduction in inference latency. AIBrix also supports unified AI runtime which streamlines model management while maintaining vendor-agnostic engine compatibility. For large-scale multi-node inference, AIBrix employs hybrid orchestration -- leveraging Kubernetes for coarse-grained scheduling and Ray for fine-grained execution -- to balance efficiency and flexibility. Additionally, an SLO-driven GPU optimizer dynamically adjusts resource allocations, optimizing heterogeneous serving to maximize cost efficiency while maintaining service guarantees. Finally, AIBrix enhances system reliability with AI accelerator diagnostic tools, enabling automated failure detection and mock-up testing to improve fault resilience. AIBrix is available at https://github.com/vllm-project/aibrix.