相关论文: Efficient Context Scaling with LongCat ZigZag Atte…

Scaling sequence length has become a critical demand in the era of large language models. However, existing methods struggle with either computational complexity or model expressivity, rendering the maximum sequence length restricted. To…

Processing long contexts remains a challenge for large language models (LLMs) due to the quadratic computational and memory overhead of the self-attention mechanism and the substantial KV cache sizes during generation. We propose LLoCO, a…

Diffusion Large Language Models (dLLMs) deliver strong long-context processing capability in a non-autoregressive decoding paradigm. However, the considerable computational cost of bidirectional full attention limits the inference…

Long-context agentic workflows have emerged as a defining use case for large language models, making attention efficiency critical for both inference speed and serving cost. Sparse attention addresses this challenge effectively, and…

Long context understanding remains challenging for large language models due to their limited context windows. This paper introduces Long Input Fine-Tuning (LIFT), a novel framework for long-context modeling that can enhance the…

Large language models (LLMs) have achieved impressive performance in numerous domains but often struggle to process lengthy inputs effectively and efficiently due to limited length generalization and attention's quadratic computational…

Slim attention shrinks the context memory size by 2x for transformer models with MHA (multi-head attention), which can speed up inference by up to 2x for large context windows. Slim attention is an exact, mathematically identical…

Handling long-context sequences efficiently remains a significant challenge in large language models (LLMs). Existing methods for token selection in sequence extrapolation either employ a permanent eviction strategy or select tokens by…

An efficient attention implementation is essential for large models due to its quadratic time complexity. Fortunately, attention commonly exhibits sparsity, i.e., many values in the attention map are near zero, allowing for the omission of…

Transformers are state-of-the-art models for a variety of sequence modeling tasks. At their core is an attention function which models pairwise interactions between the inputs at every timestep. While attention is powerful, it does not…

Long-context decoding in LLMs is IO-bound: each token re-reads an ever-growing KV cache. Prior accelerations cut bytes via compression, which lowers fidelity, or selection/eviction, which restricts what remains accessible, and both can…

Reinforcement Learning (RL) has emerged as a critical driver for enhancing the reasoning capabilities of Large Language Models (LLMs). While recent advancements have focused on reward engineering or data synthesis, few studies exploit the…

Diffusion Transformers (DiTs) set the state of the art in visual generation, yet their quadratic self-attention cost fundamentally limits scaling to long token sequences. Recent Top-K sparse attention approaches reduce the computation of…

The quadratic complexity of self-attention in Transformers has hindered the processing of long text. To alleviate this problem, previous works have proposed to sparsify the attention matrix, taking advantage of the observation that crucial…

While sparse attention mitigates the computational bottleneck of long-context LLM training, its distributed training process exhibits extreme heterogeneity in both \textit{1)} sequence length and \textit{2)} sparsity sensitivity, leading to…

Inference with Transformer-based Large Language Models (LLMs) on long sequences is both costly and slow due to the quadratic complexity of the self-attention mechanism. We introduce Star Attention, a two-phase block-sparse approximation…

As long-context inference becomes central to large language models (LLMs), attention over growing key-value caches emerges as a dominant decoding bottleneck, motivating sparse attention for scalable inference. Fixed-budget top-k sparse…

The attention mechanism is the key to the success of transformers in different machine learning tasks. However, the quadratic complexity with respect to the sequence length of the vanilla softmax-based attention mechanism becomes the major…

Long-Context Transformer Models (LCTMs) are vital for real-world applications but suffer high computational costs due to attention's quadratic complexity. Block-sparse attention mitigates this by focusing computation on critical regions,…

We present a series of long-context LLMs that support effective context windows of up to 32,768 tokens. Our model series are built through continual pretraining from Llama 2 with longer training sequences and on a dataset where long texts…