A Survey of Efficient Attention Methods: Hardware-efficient, Sparse, Compact, and Linear Attention
☆284Dec 1, 2025Updated 3 months ago
Alternatives and similar repositories for Efficient_Attention_Survey
Users that are interested in Efficient_Attention_Survey are comparing it to the libraries listed below
Sorting:
- ☆227Nov 19, 2025Updated 3 months ago
- [NeurIPS'25 Spotlight] Adaptive Attention Sparsity with Hierarchical Top-p Pruning☆88Nov 29, 2025Updated 3 months ago
- [ICML2025] SpargeAttention: A training-free sparse attention that accelerates any model inference.☆954Feb 25, 2026Updated last week
- Accelerating Large-Scale Reasoning Model Inference with Sparse Self-Speculative Decoding☆93Dec 2, 2025Updated 3 months ago
- SpInfer: Leveraging Low-Level Sparsity for Efficient Large Language Model Inference on GPUs☆60Mar 25, 2025Updated 11 months ago
- A sparse attention kernel supporting mix sparse patterns☆472Jan 18, 2026Updated last month
- SLA: Beyond Sparsity in Diffusion Transformers via Fine-Tunable Sparse–Linear Attention☆284Feb 24, 2026Updated 2 weeks ago
- 🐳 Efficient Triton implementations for "Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention"☆974Feb 5, 2026Updated last month
- qwen-nsa☆87Oct 14, 2025Updated 4 months ago
- DeeperGEMM: crazy optimized version☆74May 5, 2025Updated 10 months ago
- [ICLR'25] ViDiT-Q: Efficient and Accurate Quantization of Diffusion Transformers for Image and Video Generation☆151Mar 21, 2025Updated 11 months ago
- ☆11Jan 10, 2025Updated last year
- ☆52May 19, 2025Updated 9 months ago
- A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-perfo…☆88Feb 2, 2026Updated last month
- [ICLR 2025] DuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming Heads☆527Feb 10, 2025Updated last year
- [ICML2025, NeurIPS2025 Spotlight] Sparse VideoGen 1 & 2: Accelerating Video Diffusion Transformers with Sparse Attention☆633Updated this week
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆161Oct 13, 2025Updated 4 months ago
- ☆65Apr 26, 2025Updated 10 months ago
- [ICLR2025, ICML2025, NeurIPS2025 Spotlight] Quantized Attention achieves speedup of 2-5x compared to FlashAttention, without losing end-t…☆3,192Jan 17, 2026Updated last month
- Standalone Flash Attention v2 kernel without libtorch dependency☆114Sep 10, 2024Updated last year
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆659Updated this week
- Tutorials of Extending and importing TVM with CMAKE Include dependency.☆16Oct 11, 2024Updated last year
- KsanaDiT: High-Performance DiT (Diffusion Transformer) Inference Framework for Video & Image Generation☆45Updated this week
- Code Repository of Evaluating Quantized Large Language Models☆136Sep 8, 2024Updated last year
- ☆135Aug 18, 2025Updated 6 months ago
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- Implement Flash Attention using Cute.☆102Dec 17, 2024Updated last year
- [ICLR 2026 Oral] Locality-aware Parallel Decoding for Efficient Autoregressive Image Generation☆91Feb 7, 2026Updated last month
- [ICLR2025 Spotlight] MagicPIG: LSH Sampling for Efficient LLM Generation☆250Dec 16, 2024Updated last year
- Puzzles for learning Triton, play it with minimal environment configuration!☆637Dec 28, 2025Updated 2 months ago
- [MLSys'25] QServe: W4A8KV4 Quantization and System Co-design for Efficient LLM Serving; [MLSys'25] LServe: Efficient Long-sequence LLM Se…☆817Mar 6, 2025Updated last year
- DeepSeek-V3.2-Exp DSA Warmup Lightning Indexer training operator based on tilelang☆44Nov 19, 2025Updated 3 months ago
- ☆41Oct 15, 2025Updated 4 months ago
- 🚀 Efficient implementations of state-of-the-art linear attention models☆4,474Updated this week
- [ICML 2025] XAttention: Block Sparse Attention with Antidiagonal Scoring☆269Jul 6, 2025Updated 8 months ago
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆79Aug 12, 2024Updated last year
- [NeurIPS 2025] ClusterFusion: Expanding Operator Fusion Scope for LLM Inference via Cluster-Level Collective Primitive☆66Dec 11, 2025Updated 2 months ago
- Official implementation of paper "VMoBA: Mixture-of-Block Attention for Video Diffusion Models"☆62Jul 1, 2025Updated 8 months ago
- An efficient implementation of the NSA (Native Sparse Attention) kernel☆129Jun 24, 2025Updated 8 months ago