Fast and memory-efficient exact attention
☆138Nov 3, 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:
- ☆15Oct 29, 2026Updated last week
- Tenstorrent Plugin for Triton☆14Aug 25, 2026Updated 2 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,854Updated this week
- FLA but cuTile☆27Apr 17, 2026Updated 6 months ago
- a repo to study TensorRT Plugin☆11Apr 30, 2025Updated last year
- Deploy open-source AI quickly and easily - Special Bonus Offer • AdRunpod Hub is built for open source. One-click deployment and autoscaling endpoints without provisioning your own infrastructure.
- Efficient and unified implementations for TopK-based sparse attention☆41Jul 10, 2026Updated 3 months ago
- FA4-based Relative Attention Kernel developed by TML and Colfax☆18Sep 11, 2026Updated last month
- ☆28Oct 4, 2026Updated last month
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆172Oct 13, 2025Updated last year
- [NeurIPS 2025] Official implementation of "Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning"☆32Oct 20, 2025Updated last year
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,259Updated this week
- study of cutlass☆22Nov 10, 2024Updated last year
- ☆156Mar 4, 2025Updated last year
- FP16xINT4 LLM inference kernel that can achieve near-ideal ~4x speedups up to medium batchsizes of 16-32 tokens.☆1,174Sep 4, 2024Updated 2 years ago
- Managed hosting for WordPress and PHP on Cloudways • AdManaged hosting for WordPress, Magento, Laravel, or PHP apps, on multiple cloud providers. Deploy in minutes on Cloudways by DigitalOcean.
- KV cache compression for high-throughput LLM inference☆163Feb 5, 2025Updated last year
- NVFP4 Flash-Attention 4 on BlackWell☆69Sep 26, 2026Updated last month
- a size profiler for cuda binary☆74Oct 3, 2026Updated last month
- CUDA Templates for Linear Algebra Subroutines☆102Apr 25, 2024Updated 2 years ago
- SGLang Kernel Wheel Index☆26Updated this week
- KV cache store for distributed LLM inference☆451Sep 16, 2026Updated last month
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,693Updated this week
- As the core component of the Huawei Ascend for PyTorch community, TorchNPU is a deep learning adapter plugin built by Ascend for PyTorch,…☆600Updated this week
- A sparse attention kernel supporting mix sparse patterns☆567Jan 18, 2026Updated 9 months ago
- Wordpress hosting with auto-scaling - Free Trial Offer • AdFully Managed hosting for WordPress and WooCommerce businesses that need reliable, auto-scalable performance. Cloudways SafeUpdates now available.
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆1,387Updated this week
- CUDA SGEMM optimization note☆16Oct 31, 2023Updated 3 years ago
- ☆74Mar 24, 2026Updated 7 months ago
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,885Sep 24, 2026Updated last month
- ☆13Feb 11, 2025Updated last year
- Breakable CUDA graph capture for PyTorch - capture compatible regions as CUDA graphs while running incompatible operations eagerly betwee…☆30Oct 8, 2026Updated 3 weeks ago
- Disaggregated serving system for Large Language Models (LLMs).☆847Apr 6, 2025Updated last year
- Sample-Efficient Parametric Learning from Natural Language☆13Feb 5, 2026Updated 8 months ago
- A Triton-only attention backend for vLLM☆28Jul 14, 2026Updated 3 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.
- Layered prefill changes the scheduling axis from tokens to layers and removes redundant MoE weight reloads while keeping decode stall fre…☆24Mar 9, 2026Updated 7 months ago
- LightLLM is a Python-based LLM (Large Language Model) inference and serving framework, notable for its lightweight design, easy scalabili…☆4,353Updated this week
- performance engineering☆30Jul 11, 2024Updated 2 years ago
- ☆23May 5, 2025Updated last year
- Fast and memory-efficient exact attention☆23Oct 27, 2026Updated last week
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆363Jun 10, 2025Updated last year
- Implement Flash Attention using Cute.☆113Dec 17, 2024Updated last year