Related papers: LaCache: Ladder-Shaped KV Caching for Efficient Lo…
The deployment of long-context Large Language Models (LLMs) poses significant challenges due to the intense computational cost of self-attention and the substantial memory overhead of the Key-Value Cache (KV Cache). In this paper, we…
Existing visual token compression methods for Multimodal Large Language Models (MLLMs) predominantly operate as post-encoder modules, limiting their potential for efficiency gains. To address this limitation, we propose LaCo (Layer-wise…
Running Large Language Models (LLMs) on edge devices is crucial for reducing latency, improving real-time processing, and enhancing privacy. By performing inference directly on the device, data does not need to be sent to the cloud,…
The Key-Value (KV) cache introduces substantial memory overhead during large language model (LLM) inference. Although existing vector quantization (VQ) methods reduce KV cache usage and provide flexible representational capacity across…
As the context length of current large language models (LLMs) rapidly increases, the memory demand for the Key-Value (KV) cache is becoming a bottleneck for LLM deployment and batch processing. Traditional KV cache compression methods…
Diffusion-based large language models (dLLMs), despite their promising performance, still suffer from inferior inference efficiency. This is because dLLMs rely on bidirectional attention and cannot directly benefit from the standard…
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…
Sequence-to-sequence tasks often benefit from long contexts, but the quadratic complexity of self-attention in standard Transformers renders this non-trivial. During generation, temporary representations -stored in the so-called KV…
KV caching is a fundamental technique for accelerating Large Language Model (LLM) inference by reusing key-value (KV) pairs from previous queries, but its effectiveness under limited memory is highly sensitive to the eviction policy. The…
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…
The growing complexity of LLM usage today, e.g., multi-round conversation and retrieval-augmented generation (RAG), makes contextual states (i.e., KV cache) reusable across user requests. Given the capacity constraints of GPU memory, only a…
Large language models (LLMs) face growing challenges in efficient generative inference due to the increasing memory demands of Key-Value (KV) caches, especially for long sequences. Existing eviction methods typically retain KV pairs with…
Parameter quantization for Large Language Models (LLMs) has attracted increasing attentions recently in reducing memory costs and improving computational efficiency. Early approaches have been widely adopted. However, the existing methods…
Recently, large language models (LLMs) have been able to handle longer and longer contexts. However, a context that is too long may cause intolerant inference latency and GPU memory usage. Existing methods propose mixed-precision…
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…
The increasing context window size in large language models (LLMs) has improved their ability to handle complex, long-text tasks. However, as the conversation rounds continue, it is required to store a large amount of KV cache in GPU…
Techniques enabling large language models (LLMs) to "think more" by generating and attending to intermediate reasoning steps have shown promise in solving complex problems. However, the standard approaches generate sequences of discrete…
Long-running agentic tasks, such as deep research, require multi-hop reasoning over information distributed across multiple webpages and documents. In such tasks, the LLM context is dominated by tokens from external retrieval, causing…
Autoregressive decoding in large language models (LLMs) requires caching a growing list of past key-value (KV) pairs, making long-context inference a memory-bound problem. While recent methods have explored quantizing the cache, evicting…
For the efficient inference of Large Language Models (LLMs), the effective compression of key-value (KV) cache is essential. Three main types of KV cache compression techniques, namely sparsity, channel compression, and quantization, have…