相关论文: Meta-Soft: Leveraging Composable Meta-Tokens for C…

Key-Value (KV) caching is a common technique to enhance the computational efficiency of Large Language Models (LLMs), but its memory overhead grows rapidly with input length. Prior work has shown that not all tokens are equally important…

Key-Value (KV) cache has become a bottleneck of LLMs for long-context generation. Despite the numerous efforts in this area, the optimization for the decoding phase is generally ignored. However, we believe such optimization is crucial,…

Efficient Key-Value (KV) cache management is essential for processing long text sequences in large language models (LLMs), where memory constraints often limit performance. Conventional KV eviction strategies, such as top-k selection based…

Long-context decoding is increasingly limited by KV-cache memory traffic since each generated token attends over a cache whose size grows linearly with context length. Existing sparse decoding methods reduce this cost by selecting subsets…

Large language models (LLMs) can now handle longer sequences of tokens, enabling complex tasks like book understanding and generating lengthy novels. However, the key-value (KV) cache required for LLMs consumes substantial memory as context…

Efficiently serving Large Language Models (LLMs) with persistent Prefix Key-Value (KV) Cache is critical for applications like conversational search and multi-turn dialogue. Serving a request requires loading the pre-computed prefix KV…

Multimodal large language models (MLLMs) have demonstrated great performance on visual question answering (VQA). When it comes to knowledge-based Visual Question Answering (KB-VQA), MLLMs may lack the specialized domain knowledge needed to…

Large language models (LLMs) with extended context windows have become increasingly prevalent for tackling complex tasks. However, the substantial Key-Value (KV) cache required for long-context LLMs poses significant deployment challenges.…

Multimodal Large Language Models (MLLMs) have advanced unified reasoning over text, images, and videos, but their inference is hindered by the rapid growth of key-value (KV) caches. Each visual input expands into thousands of tokens,…

Large language models (LLMs) have demonstrated strong capabilities in processing long contexts, enabling them to tackle tasks involving long textual inputs such as multi-turn conversations, legal documents, or retrieved documents in…

Traditional KV cache eviction strategies, which discard less critical KV-pairs based on attention scores, often degrade generation quality, causing context loss or hallucinations. Recent efforts shift toward KV merging, merging eviction…

LLMs are seeing growing use for applications which require large context windows, and with these large context windows KV cache activations surface as the dominant contributor to memory consumption during inference. Quantization is a…

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…

Soft context compression reduces the computational workload of processing long contexts in LLMs by encoding long context into a smaller number of latent tokens. However, existing frameworks apply uniform compression ratios, failing to…

Transformer-based large language models (LLMs) have already achieved remarkable results on long-text tasks, but the limited GPU memory (VRAM) resources struggle to accommodate the linearly growing demand for key-value (KV) cache as the…

The quadratic complexity and indefinitely growing key-value (KV) cache of standard Transformers pose a major barrier to long-context processing. To overcome this, we introduce the Collaborative Memory Transformer (CoMeT), a novel…

While chain-of-thought (CoT) reasoning enables LLMs to solve challenging reasoning tasks, the linear growth of the KV cache leads to substantial memory and inference overhead. Existing approaches such as context compression and multi-token…

Incorporating external knowledge in large language models (LLMs) enhances their utility across diverse applications, but existing methods have trade-offs. Retrieval-Augmented Generation (RAG) fetches evidence via similarity search, but key…

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…

Despite the significant success of large language models (LLMs), their extensive memory requirements pose challenges for deploying them in long-context token generation. The substantial memory footprint of LLM decoders arises from the…