Related papers: Accelerating Prefilling via Decoding-time Contribu…

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…

The increasing demand for long-context modeling in large language models (LLMs) is bottlenecked by the quadratic complexity of the standard self-attention mechanism. The community has proposed sparse attention to mitigate this issue.…

Due to the auto-regressive nature of current video large language models (Video-LLMs), the inference latency increases as the input sequence length grows, posing challenges for the efficient processing of video sequences that are usually…

This paper proposes Block-Filtered Long-Context Attention (BFLA), a training-free sparse prefill attention mechanism for long-context inference. BFLA adopts a two-stage design. In Stage 1, query and key sequences are compressed into coarse…

Long-sequence processing is a critical capability for modern large language models. However, the self-attention mechanism in the standard Transformer architecture faces severe computational and memory bottlenecks when processing long…

Large reasoning models (LRMs) achieve state-of-the-art performance on challenging benchmarks by generating long chains of intermediate steps, but their inference cost is dominated by decoding, where each new token must attend to the entire…

We consider the problem of accurate sparse fine-tuning of large language models (LLMs), that is, fine-tuning pretrained LLMs on specialized tasks, while inducing sparsity in their weights. On the accuracy side, we observe that standard…

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…

Transformer-based architectures have become the prevailing backbone of large language models. However, the quadratic time and memory complexity of self-attention remains a fundamental obstacle to efficient long-context modeling. To address…

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…

Diffusion Transformers, particularly for video generation, achieve remarkable quality but suffer from quadratic attention complexity, leading to prohibitive latency. Existing acceleration methods face a fundamental trade-off: dynamically…

Transformer-based language models have found many diverse applications requiring them to process sequences of increasing length. For these applications, the causal self-attention -- which is the only component scaling quadratically w.r.t.…

Large Language Models (LLMs) have become the central paradigm in artificial intelligence, yet the core computational primitive of attention has remained structurally unchanged. Local Linear Attention (LLA) is an attention mechanism derived…

The prefill stage of large language model (LLM) inference is a key computational bottleneck for long-context workloads. At short-to-moderate context lengths (1K--16K tokens), Feed-Forward Networks (FFNs) dominate this cost, accounting for…

Current hierarchical attention methods, such as NSA and InfLLMv2, select the top-k relevant key-value (KV) blocks based on coarse attention scores and subsequently apply fine-grained softmax attention on the selected tokens. However, the…

Existing sparse attention methods primarily target inference-time acceleration by selecting critical tokens under predefined sparsity patterns. However, they often fail to bridge the training-inference gap and lack the capacity for…

Multimodal Large Language Models (MLLMs) have achieved remarkable success in vision understanding, reasoning, and interaction. However, the inference computation and memory increase progressively with the generation of output tokens during…

With the increasing volumes of Large Language Models (LLMs) and the expanding context lengths, attention computation has become a key performance bottleneck in LLM serving. For fast attention computation, recent practices often parallelize…

Diffusion Transformers (DiTs) have shown remarkable performance in generating high-quality videos. However, the quadratic complexity of 3D full attention remains a bottleneck in scaling DiT training, especially with high-definition, lengthy…

Transformer-based large language models (LLMs) excel in natural language processing tasks by capturing long-range dependencies through self-attention mechanisms. However, long-context modeling faces significant computational inefficiencies…