相关论文: GhostServe: A Lightweight Checkpointing System in …

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…

Recent large language models (LLMs) with enormous model sizes use many GPUs to meet memory capacity requirements incurring substantial costs for token generation. To provide cost-effective LLM inference with relaxed latency constraints,…

Distributed prefix caching accelerates long-context LLM serving by reusing KV cache entries for common context prefixes. However, KV cache fetches can become a bottleneck when network bandwidth is limited. Compression mitigates the…

Global KV-cache sharing is an effective optimization for accelerating large language model (LLM) inference, yet it introduces an API-visible timing side channel that lets adversaries infer sensitive user inputs from shared entries, leading…

Key-Value (KV) cache has become a de facto component of modern Large Vision-Language Models (LVLMs) for inference. While it enhances decoding efficiency in Large Language Models (LLMs), its direct adoption in LVLMs introduces substantial…

LLM inference and serving systems have become security-critical infrastructure; however, many of their most concerning failures arise from the serving layer rather than from model behavior alone. Modern inference engines combine KV cache,…

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…

This paper presents ServerlessLLM, a distributed system designed to support low-latency serverless inference for Large Language Models (LLMs). By harnessing the substantial near-GPU storage and memory capacities of inference servers,…

Serving large language models (LLMs) efficiently remains challenging due to the high memory and latency overhead of key-value (KV) cache access during autoregressive decoding. We present \textbf{TinyServe}, a lightweight and extensible…

Serving long-context LLMs is costly because attention computation grows linearly with context length. Dynamic sparse attention algorithms (DSAs) mitigate this by attending only to the key-value (KV) cache of critical tokens. However, with…

The widespread of Large Language Models (LLMs) marks a significant milestone in generative AI. Nevertheless, the increasing context length and batch size in offline LLM inference escalate the memory requirement of the key-value (KV) cache,…

Multi-modal Large Language Models (MLLMs) serving systems commonly employ KV-cache compression to reduce memory footprint. However, existing compression methods introduce significant processing overhead and queuing delays, particularly in…

Large language models (LLMs) power a new generation of interactive AI applications exemplified by ChatGPT. The interactive nature of these applications demands low latency for LLM inference. Existing LLM serving systems use…

The Key-Value (KV) cache, which stores intermediate attention computations (Key and Value pairs) to avoid redundant calculations, is a fundamental mechanism for accelerating Large Language Model (LLM) inference. However, this efficiency…

LLM inference is essential for applications like text summarization, translation, and data analysis, but the high cost of GPU instances from Cloud Service Providers (CSPs) like AWS is a major burden. This paper proposes InferSave, a…

Recent large language models (LLMs) are rapidly extending their context windows, yet inference throughput lags due to increasing GPU memory and bandwidth demands. This is because the key-value (KV) cache, an intermediate structure storing…

How to efficiently serve LLMs in practice has become exceptionally challenging due to their prohibitive memory and computation requirements. In this study, we investigate optimizing the KV cache, whose memory footprint poses a critical…

As large language models (LLMs) continue to scale, the memory footprint of key-value (KV) caches during inference has become a significant bottleneck. Existing approaches primarily focus on compressing KV caches within a single prompt or…

Tensor parallelism (TP) enables large language models (LLMs) to scale inference efficiently across multiple GPUs, but its tight coupling makes systems fragile: a single GPU failure can halt execution, trigger costly KVCache recomputation,…

Large language model (LLM) serving demands low latency and high throughput, but high load variability makes it challenging to achieve high GPU utilization. In this paper, we identify a synergetic but overlooked opportunity to co-serve…