Fast and memory-efficient exact attention
☆134Aug 6, 2026Updated this week
Alternatives and similar repositories for flash-attention
Users that are interested in flash-attention are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- FlashInfer: Kernel Library for LLM Serving☆6,133Updated this week
- FLA but cuTile☆27Apr 17, 2026Updated 3 months ago
- [NeurIPS 2025] Official implementation of "Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning"☆32Oct 20, 2025Updated 9 months ago
- FA4-based Relative Attention Kernel developed by TML and Colfax☆18Jul 17, 2026Updated 3 weeks ago
- study of cutlass☆22Nov 10, 2024Updated last year
- Deploy on Railway without the complexity - Free Credits Offer • AdConnect your repo and Railway handles the rest with instant previews. Quickly provision container image services, databases, and storage volumes.
- ☆156Mar 4, 2025Updated last year
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆170Oct 13, 2025Updated 9 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,058Updated this week
- CUDA SGEMM optimization note☆15Oct 31, 2023Updated 2 years ago
- KV cache store for distributed LLM inference☆424Nov 13, 2025Updated 8 months ago
- CUDA Templates for Linear Algebra Subroutines☆102Apr 25, 2024Updated 2 years ago
- A sparse attention kernel supporting mix sparse patterns☆544Jan 18, 2026Updated 6 months ago
- a size profiler for cuda binary☆71Jan 15, 2026Updated 6 months ago
- SGLang Kernel Wheel Index☆24Updated this week
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- ☆71Mar 24, 2026Updated 4 months ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆1,297Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,629Updated this week
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,217Updated this week
- A Triton-only attention backend for vLLM☆28Jul 14, 2026Updated 3 weeks ago
- ☆60Updated this week
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,208Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆1,184Updated this week
- Layered prefill changes the scheduling axis from tokens to layers and removes redundant MoE weight reloads while keeping decode stall fre…☆20Mar 9, 2026Updated 5 months ago
- Deploy to Railway using AI coding agents - Free Credits Offer • AdUse Claude Code, Codex, OpenCode, and more. Autonomous software development now has the infrastructure to match with Railway.
- A collection of out-of-tree extensions for the Triton language and compiler☆33Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆828Apr 6, 2025Updated last year
- ☆22May 5, 2025Updated last year
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆4,216Updated this week
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆332Jun 10, 2025Updated last year
- Implement Flash Attention using Cute.☆111Dec 17, 2024Updated last year
- performance engineering☆30Jul 11, 2024Updated 2 years ago
- ☆24Jun 10, 2026Updated 2 months ago
- Fast and memory-efficient exact attention☆23Jun 26, 2026Updated last month
- End-to-end encrypted email - Proton Mail • AdSpecial offer: 40% Off Yearly / 80% Off First Month. All Proton services are open source and independently audited for security.
- KV cache compression for high-throughput LLM inference☆159Feb 5, 2025Updated last year
- Design hardware-friendly model architectures and migrate existing LLMs with minimal performance loss☆497Jul 14, 2026Updated 3 weeks ago
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,193Jul 30, 2026Updated last week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆400Jul 10, 2025Updated last year
- MetaAttention: A Unified and Performant Attention Framework Across Hardware Backends(PPoPP'26)☆17Updated this week
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆490Jul 5, 2026Updated last month
- ☆53May 19, 2025Updated last year