Related papers: Apt-Serve: Adaptive Request Scheduling on Hybrid C…

Recent advancements in Audio-Video Large Language Models (AV-LLMs) have enhanced their capabilities in tasks like audio-visual question answering and multimodal dialog systems. Video and audio introduce an extended temporal dimension,…

Large Language Models (LLMs) are increasingly deployed in scenarios demanding ultra-long context reasoning, such as agentic workflows and deep research understanding. However, long-context inference is constrained by the KV cache, a…

Recently, large vision-language models (LVLMs) have rapidly gained popularity for their strong generation and reasoning capabilities given diverse multimodal inputs. However, these models incur significant computational and memory overhead…

Retrieval-Augmented Generation (RAG) systems enhance the performance of large language models (LLMs) by incorporating supplementary retrieved documents, enabling more accurate and context-aware responses. However, integrating these external…

Clients are evolving beyond chat completion, and now include a variety of innovative inference-time scaling and deep reasoning techniques. At the same time, inference servers remain heavily optimized for chat completion. Prior work has…

The evolution of Large Language Model (LLM) serving towards complex, distributed architectures--specifically the P/D-separated, large-scale DP+EP paradigm--introduces distinct scheduling challenges. Unlike traditional deployments where…

Recent advancements in Large Language Model (LLM) agents have enabled complex multi-turn agentic tasks requiring extensive tool calling, where conversations can span dozens of API calls with increasingly large context windows. However,…

Speculative decoding accelerates Large Language Model (LLM) inference by employing a small speculative model (SSM) to generate multiple candidate tokens and verify them using the LLM in parallel. This technique has been widely integrated…

LAPS identifies and disaggregates requests with different prompt lengths in LLM serving to reduce TTFT latency. While recent systems have decoupled the prefill and decode stages to improve throughput, they still rely on unified scheduling…

Autoregressive decoding with generative Large Language Models (LLMs) on accelerators (GPUs/TPUs) is often memory-bound where most of the time is spent on transferring model parameters from high bandwidth memory (HBM) to cache. On the other…

The scaling of inference computation has unlocked the potential of long-context large language models (LLMs) across diverse settings. For knowledge-intensive tasks, the increased compute is often allocated to incorporate more external…

Large language model (LLM) serving faces the dual challenge of meeting strict user-specific service-level objectives (SLOs) while minimizing computational cost under dynamic, multi-task workloads. Existing approaches either rely on static…

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…

The growing adoption of Large Language Models (LLMs) across various domains has driven the demand for efficient and scalable AI-serving solutions. Deploying LLMs requires optimizations to manage their significant computational and data…

Large Language Models (LLMs), such as GPT, have revolutionized artificial intelligence by enabling nuanced understanding and generation of human-like text across a wide range of applications. However, the high computational and financial…

As machine learning techniques are applied to a widening range of applications, high throughput machine learning (ML) inference servers have become critical for online service applications. Such ML inference servers pose two challenges:…

Large language models (LLMs) have been widely applied but face challenges in efficient inference. While quantization methods reduce computational demands, ultra-low bit quantization with arbitrary precision is hindered by limited GPU Tensor…

Large language model (LLM) inference often suffers from high latency, particularly in resource-constrained environments such as on-device or edge deployments. To address this challenge, we present StorInfer, a novel storage-assisted LLM…

The increasing scale and complexity of large language models (LLMs) pose significant inference latency challenges, primarily due to their autoregressive decoding paradigm characterized by the sequential nature of next-token prediction. By…

Conventional recommendation systems (RSs) are typically optimized to enhance performance metrics uniformly across all training samples. This makes it hard for data-driven RSs to cater to a diverse set of users due to the varying properties…