Related papers: KVCrush: Key value cache size-reduction using simi…
KV cache pruning has emerged as a promising technique for reducing memory and computation costs in long-context auto-regressive generation. Existing methods for vision-language models (VLMs) typically rely on self-attention scores from…
Large language models (LLMs) are increasingly applied in long-context scenarios such as multi-turn conversations. However, long contexts pose significant challenges for inference efficiency, including high memory overhead from Key-Value…
Large Language Models (LLMs), epitomized by ChatGPT's release in late 2022, have revolutionized various industries with their advanced language comprehension. However, their efficiency is challenged by the Transformer architecture's…
KV cache in autoregressive LLMs eliminates redundant recomputation but has emerged as the dominant memory and bandwidth bottleneck during inference, notably with long contexts and test-time scaling. KV quantization is a key lever for…
Large Language Models (LLMs) have demonstrated remarkable proficiency across a wide range of tasks. However, LLMs often require larger batch sizes to enhance throughput or longer context lengths to meet task demands, which significantly…
KV cache compression is critical for efficient long-context LLM inference. Approaches that reduce the per-pair footprint -- quantization and low-rank decomposition -- are orthogonal to those that reduce the sequence length of the cache.…
Retrieval-augmented generation improves large language models' accuracy by adding relevant retrieved text to the prompt. Chunk level caching (CLC) accelerates inference by precomputing KV caches for these retrieved chunks and reusing them.…
Large language models (LLMs) with extended context windows enable powerful downstream applications but impose significant memory overhead, as caching all key-value (KV) states scales linearly with sequence length and batch size. Existing…
Video large language models (VideoLLMs) have demonstrated the capability to process longer video inputs and enable complex reasoning and analysis. However, due to the thousands of visual tokens from the video frames, the key-value (KV)…
Large Language Models (LLMs) have achieved remarkable progress across reasoning, generation, and decision-making tasks, yet deploying them on mobile, embedded, and edge devices remains particularly challenging. On-device LLM inference is…
Inference for Large Language Models (LLMs) is computationally demanding. To reduce the cost of auto-regressive decoding, Key-Value (KV) cache is used to store intermediate activations, which significantly lowers the computational overhead…
Multimodal Large Language Models (MLLMs) have demonstrated remarkable performance across diverse applications. However, their computational overhead during deployment remains a critical bottleneck. While Key-Value (KV) caching effectively…
Key-Value (KV) cache remains a major bottleneck for deploying Large Language Models (LLMs) in long-generation tasks. Prior work often applies uniform compression across both prefill and decoding caches, but compressing the prefill cache…
Visual autoregressive modeling (VAR) via next-scale prediction has emerged as a scalable image generation paradigm. While Key and Value (KV) caching in large language models (LLMs) has been extensively studied, next-scale prediction…
Generating long sequences of tokens given a long-context input is a very compute-intensive inference scenario for large language models (LLMs). One prominent inference speed-up approach is to construct a smaller key-value (KV) cache,…
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…
The growing size of Large Language Models (LLMs) makes efficient inference challenging, primarily due to the memory demands of the autoregressive Key-Value (KV) cache. Existing eviction or compression methods reduce cost but rely on…
Interacting with humans through multi-turn conversations is a fundamental feature of large language models (LLMs). However, existing LLM serving engines executing multi-turn conversations are inefficient due to the need to repeatedly…
We describe KVLink, an approach for efficient key-value (KV) cache reuse in large language models (LLMs). In many LLM applications, different inputs can share overlapping context, such as the same retrieved document appearing in multiple…
As large language models (LLMs) process increasing context windows, the memory usage of KV cache has become a critical bottleneck during inference. The mainstream KV compression methods, including KV pruning and KV quantization, primarily…