Related papers: Paged Attention Meets FlexAttention: Unlocking Lon…

Scaling Transformers to longer sequence lengths has been a major problem in the last several years, promising to improve performance in language modeling and high-resolution image understanding, as well as to unlock new applications in…

Large language models (LLMs) support long-context inference but suffer from substantial memory and runtime overhead due to Key-Value (KV) Cache growth. Existing KV Cache eviction methods primarily rely on local attention weights, neglecting…

Large language models face significant computational and memory challenges when processing long contexts. During inference, efficient management of the key-value (KV) cache, which stores intermediate activations for autoregressive…

Large language models (LLMs) are typically served from clusters of GPUs/NPUs that consist of large number of devices. Unfortunately, communication between these devices incurs significant overhead, increasing the inference latency and cost…

Long-horizon LLM inference turns the key--value (KV) cache into the dominant GPU memory consumer and makes per-token attention increasingly expensive. Many common eviction policies use static recency windows or historical attention, leaving…

Modern large language models (LLMs) extend context lengths to millions of tokens, enabling coherent, personalized responses grounded in long conversational history. However, the Key-Value (KV) cache grows linearly with the extended dialogue…

Current high-resolution vision-language models encode images as high-resolution image tokens and exhaustively take all these tokens to compute attention, which significantly increases the computational cost. To address this problem, we…

The quadratic computational complexity of the attention mechanism in current Large Language Models (LLMs) renders inference with long contexts prohibitively expensive. To address this challenge, various approaches aim to retain critical…

Finetuning large language models (LLMs) is essential for task adaptation, yet today's serving stacks isolate inference and finetuning on separate GPU clusters -- wasting resources and under-utilizing hardware. We introduce FlexLLM, the…

The quadratic complexity of the attention mechanism and the substantial memory footprint of the Key-Value (KV) cache present severe computational and memory challenges for Large Language Models (LLMs) processing long contexts. Existing…

Long Chain-of-Thought (CoT) reasoning has significantly advanced the capabilities of Large Language Models (LLMs), but this progress is accompanied by substantial memory and latency overhead from the extensive Key-Value (KV) cache. Although…

Recently, sharing key-value (KV) cache across layers has been found effective in efficient inference of large language models (LLMs). To systematically investigate different techniques of cross-layer KV sharing, we propose a unified…

With the advancements in long-context inference capabilities of large language models (LLMs), the KV cache has become one of the foundational components. However, its substantial GPU memory consumption makes KV cache compression a key…

Supporting long-context LLMs is challenging due to the substantial memory demands of the key-value (KV) cache. Existing offloading systems store the full cache in host memory and selectively fetch critical entries during decoding, but this…

Large Language Models(LLMs) have had a profound impact on AI applications, particularly in the domains of long-text comprehension and generation. KV Cache technology is one of the most widely used techniques in the industry. It ensures…

Generative reasoning with large language models (LLMs) often involves long decoding sequences, leading to substantial memory and latency overheads from accumulating key-value (KV) caches. While existing KV compression methods primarily…

The increasing adoption of large language models (LLMs) on heterogeneous computing platforms poses significant challenges to achieving high inference efficiency. To address these efficiency bottlenecks across diverse platforms, this paper…

Long-context inference in large language models is bottlenecked by Key--Value (KV) cache loading during the decoding stage, where the sequential nature of generation requires repeatedly transferring the KV cache from off-chip High-Bandwidth…

The memory-for-computation paradigm of KV caching is essential for accelerating large language model (LLM) inference service, but limited GPU high-bandwidth memory (HBM) capacity motivates offloading the KV cache to cheaper external storage…

The efficiency of Large Language Model~(LLM) inference is often constrained by substantial memory bandwidth and capacity demands. Existing techniques, such as pruning, quantization, and mixture of experts/depth, reduce memory capacity…