mit-han-lab / x-attentionLinks
[ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring
☆211Updated 3 weeks ago
Alternatives and similar repositories for x-attention
Users that are interested in x-attention are comparing it to the libraries listed below
Sorting:
- A sparse attention kernel supporting mix sparse patterns☆262Updated 5 months ago
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆124Updated 2 months ago
- Official implementation of "Fast-dLLM: Training-free Acceleration of Diffusion LLM by Enabling KV Cache and Parallel Decoding"☆320Updated this week
- Efficient triton implementation of Native Sparse Attention.☆177Updated 2 months ago
- [ICML 2025] SparseLoRA: Accelerating LLM Fine-Tuning with Contextual Sparsity☆48Updated 3 weeks ago
- [ICLR 2025] COAT: Compressing Optimizer States and Activation for Memory-Efficient FP8 Training☆218Updated last month
- [CoLM'25] The official implementation of the paper <MoA: Mixture of Sparse Attention for Automatic Large Language Model Compression>☆141Updated 3 weeks ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆307Updated 3 weeks ago
- 16-fold memory access reduction with nearly no loss☆102Updated 4 months ago
- ☆123Updated 2 months ago
- 🔥 A minimal training framework for scaling FLA models☆209Updated last month
- ☆136Updated 5 months ago
- SeerAttention: Learning Intrinsic Sparse Attention in Your LLMs☆140Updated 2 weeks ago
- [ICLR 2025] Palu: Compressing KV-Cache with Low-Rank Projection☆128Updated 5 months ago
- Official PyTorch implementation of the paper "dLLM-Cache: Accelerating Diffusion Large Language Models with Adaptive Caching" (dLLM-Cache…☆130Updated 2 weeks ago
- [ICLR 2025] Mixture Compressor for Mixture-of-Experts LLMs Gains More☆48Updated 5 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆108Updated last month
- ☆88Updated 2 months ago
- [NeurIPS 2024] The official implementation of ZipCache: Accurate and Efficient KV Cache Quantization with Salient Token Identification☆23Updated 4 months ago
- ☆54Updated 3 weeks ago
- ☆326Updated this week
- A curated list of recent papers on efficient video attention for video diffusion models, including sparsification, quantization, and cach…☆32Updated 2 weeks ago
- [ICLR2025] Codebase for "ReMoE: Fully Differentiable Mixture-of-Experts with ReLU Routing", built on Megatron-LM.☆85Updated 7 months ago
- Triton implementation of FlashAttention2 that adds Custom Masks.☆127Updated 11 months ago
- GEAR: An Efficient KV Cache Compression Recipefor Near-Lossless Generative Inference of LLM☆165Updated last year
- ☆113Updated last month
- ☆228Updated last month
- Flash-Muon: An Efficient Implementation of Muon Optimizer☆149Updated last month
- ☆171Updated 6 months ago
- The Official Implementation of Ada-KV: Optimizing KV Cache Eviction by Adaptive Budget Allocation for Efficient LLM Inference☆87Updated last month