Related papers: Lag-Relative Sparse Attention In Long Context Trai…

Attention serves as the fundamental mechanism for long-context modeling in large language models (LLMs), yet dense attention becomes structurally prohibitive for long sequences due to its quadratic complexity. Consequently, sparse attention…

Large Reasoning Models (LRMs) have shown promising accuracy improvements on complex problem-solving tasks. While these models have attained high accuracy by leveraging additional computation at test time, they need to generate long…

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…

Large language models (LLMs) have demonstrated remarkable performance on long-context tasks, but are often bottlenecked by memory constraints. Namely, the KV cache, which is used to significantly speed up attention computations, grows…

The evolution of large language models (LLMs) towards applications with ultra-long contexts faces challenges posed by the high computational and memory costs of the Transformer architecture. While existing sparse and linear attention…

Sparse attention methods exploit the inherent sparsity in attention to speed up the prefilling phase of long-context inference, mitigating the quadratic complexity of full attention computation. While existing sparse attention methods rely…

This paper tackles the memory hurdle of processing long context sequences in Large Language Models (LLMs), by presenting a novel approach, Dropping In Convolutions for Long Context Compression (LoCoCo). LoCoCo employs only a fixed-size…

The per-token cost of transformer inference scales with context length, preventing its application to lifelong in-context learning. Linear attention is an efficient alternative that maintains a constant memory footprint, even on infinite…

As Large Language Models (LLMs) scale to support context windows exceeding one million tokens, the linear growth of Key-Value (KV) cache imposes severe memory capacity and bandwidth bottlenecks, constraining the efficiency of long-context…

Long-context inference in Large Language Models (LLMs) is bottlenecked by the quadratic computation complexity of attention and the substantial memory footprint of Key-Value (KV) caches. While existing sparse attention mechanisms attempt to…

Large Language Models (LLMs) use key-value (KV) cache to reduce redundant computation in autoregressive generation. However, the KV cache size increases linearly during generation, leading to excessive memory usage, especially for long…

The computational difficulties of large language model (LLM) inference remain a significant obstacle to their widespread deployment. The need for many applications to support long input sequences and process them in large batches typically…

The deployment of large language models (LLMs) is often hindered by the extensive memory requirements of the Key-Value (KV) cache, especially as context lengths increase. Existing approaches to reduce the KV cache size involve either…

Long-context Large Language Models (LLMs) face significant memory bottlenecks during inference due to the linear growth of key-value (KV) cache with sequence length. While individual optimization techniques like KV cache quantization,…

Long-context understanding is crucial for many NLP applications, yet transformers struggle with efficiency due to the quadratic complexity of self-attention. Sparse attention methods alleviate this cost but often impose static, predefined…

Emerging Large Language Model (LLM) applications require long input context in order to perform complex tasks like document analysis and code generation. For these long context length applications, the length of the input prompt poses a…

In long-context large language model (LLM) inference, the prefill stage dominates computation due to self-attention over the complete input context. Sparse attention significantly reduces self-attention computation by limiting each token's…

As large language models (LLMs) improve their capabilities in handling complex tasks, the issues of computational cost and efficiency due to long prompts are becoming increasingly prominent. To accelerate model inference and reduce costs,…

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,…

Large Language Models (LLMs) have demonstrated remarkable proficiency in language comprehension and generation; however, their widespread adoption is constrained by substantial bandwidth and computational demands. While pruning and low-rank…