Related papers: LServe: Efficient Long-sequence LLM Serving with U…
Reducing the key-value (KV) cache burden in Large Language Models (LLMs) significantly accelerates inference. Dynamically selecting critical KV caches during decoding helps maintain performance. Existing methods use random linear hashing to…
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,…
The Key-Value (KV) cache in generative large language models (LLMs) introduces substantial memory overhead. Existing works mitigate this burden by offloading or compressing the KV cache. However, loading the entire cache incurs significant…
Context lengths of Large Language Models (LLMs) have exploded in recent years, with 128k-token context becoming a standard and million-token context becoming a reality. Efficiently supporting long-context inference remains challenging as…
Due to the auto-regressive nature of current video large language models (Video-LLMs), the inference latency increases as the input sequence length grows, posing challenges for the efficient processing of video sequences that are usually…
Multi-head Latent Attention (MLA) is an innovative architecture proposed by DeepSeek, designed to ensure efficient and economical inference by significantly compressing the Key-Value (KV) cache into a latent vector. Compared to MLA,…
Large language models (LLMs) demonstrate strong capabilities across a wide range of complex tasks and are increasingly deployed at scale, placing significant demands on inference efficiency. Prior work typically decomposes inference into…
Large language models (LLMs) are increasingly employed for complex tasks that process multiple generation calls in a tree structure with shared prefixes of tokens, including few-shot prompting, multi-step reasoning, speculative decoding,…
Large Language Models (LLMs) have been widely deployed in a variety of applications, and the context length is rapidly increasing to handle tasks such as long-document QA and complex logical reasoning. However, long context poses…
With reasoning becoming the generative paradigm for large language models (LLMs), the memory bottleneck caused by KV cache during the decoding phase has become a critical factor limiting high-concurrency service. Although existing KV cache…
Large Language Model (LLM) serving must meet stringent Service Level Objectives (SLOs) for both the prefill and decode phases. Some existing solutions disaggregate the two phases, causing potential resource idleness or compute redundancy.…
Transformer based Large Language Models (LLMs) have been widely used in many fields, and the efficiency of LLM inference becomes hot topic in real applications. However, LLMs are usually complicatedly designed in model structure with…
Large language models have achieved notable success across various domains, yet efficient inference is still limited by the quadratic computation complexity of the attention mechanism. The inference consists of prefilling and decoding…
The linear memory growth of the KV cache poses a significant bottleneck for LLM inference in long-context tasks. Existing static compression methods often fail to preserve globally important information. Although recent dynamic retrieval…
Edge acceleration for large language models is crucial for their widespread application; however, achieving fast attention inference and efficient decoding on resource-constrained edge accelerators remains challenging. This paper presents…
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…
Global cloud service providers handle inference workloads for Large Language Models (LLMs) that span latency-sensitive (e.g., chatbots) and insensitive (e.g., report writing) tasks, resulting in diverse and often conflicting Service Level…
The rise of large language models (LLMs) has created new opportunities across various fields but has also introduced significant challenges in resource management. Current LLM serving systems face a fundamental tension: balancing serving…
We demonstrate that unstructured sparsity significantly improves KV cache compression for LLMs, enabling sparsity levels up to 70% without compromising accuracy or requiring fine-tuning. We conduct a systematic exploration of pruning…
LLM decoding is bottlenecked for large batches and long contexts by loading the key-value (KV) cache from high-bandwidth memory, which inflates per-token latency, while the sequential nature of decoding limits parallelism. We analyze the…