Fast and memory-efficient exact attention
☆135Sep 8, 2026Updated last 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☆6,452Updated this week
- FLA but cuTile☆27Apr 17, 2026Updated 5 months ago
- [NeurIPS 2025] Official implementation of "Reasoning Path Compression: Compressing Generation Trajectories for Efficient LLM Reasoning"☆32Oct 20, 2025Updated 11 months ago
- FA4-based Relative Attention Kernel developed by TML and Colfax☆18Sep 11, 2026Updated last week
- study of cutlass☆22Nov 10, 2024Updated last year
- Managed Database hosting by DigitalOcean • AdPostgreSQL, MySQL, MongoDB, Kafka, Valkey, and OpenSearch available. Automatically scale up storage and focus on building your apps.
- ☆156Mar 4, 2025Updated last year
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆172Oct 13, 2025Updated 11 months ago
- Train speculative decoding models effortlessly and port them smoothly to SGLang serving.☆1,178Updated this week
- CUDA SGEMM optimization note☆16Oct 31, 2023Updated 2 years ago
- KV cache store for distributed LLM inference☆439Updated this week
- CUDA Templates for Linear Algebra Subroutines☆102Apr 25, 2024Updated 2 years ago
- a size profiler for cuda binary☆71Jan 15, 2026Updated 8 months ago
- A sparse attention kernel supporting mix sparse patterns☆555Jan 18, 2026Updated 8 months ago
- SGLang Kernel Wheel Index☆26Updated this week
- Virtual machines for every use case on DigitalOcean • AdGet dependable uptime with 99.99% SLA, simple security tools, and predictable monthly pricing with DigitalOcean's virtual machines, called Droplets.
- ☆73Mar 24, 2026Updated 5 months ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆1,341Updated this week
- Tile-Based Runtime for Ultra-Low-Latency LLM Inference☆1,783Aug 13, 2026Updated last month
- CUDA Templates and Python DSLs for High-Performance Linear Algebra☆10,457Updated this week
- A Triton-only attention backend for vLLM☆28Jul 14, 2026Updated 2 months ago
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆6,614Updated this week
- NVIDIA Inference Xfer Library (NIXL)☆1,263Updated this week
- Disaggregated serving system for Large Language Models (LLMs).☆837Apr 6, 2025Updated last year
- A collection of out-of-tree extensions for the Triton language and compiler☆38Updated this week
- 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.
- ☆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…☆4,295Updated 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 6 months ago
- Implement Flash Attention using Cute.☆111Dec 17, 2024Updated last year
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆357Jun 10, 2025Updated last year
- performance engineering☆30Jul 11, 2024Updated 2 years ago
- ☆26Jun 10, 2026Updated 3 months ago
- Fast and memory-efficient exact attention☆23Jun 26, 2026Updated 2 months ago
- KV cache compression for high-throughput LLM inference☆161Feb 5, 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.
- Design hardware-friendly model architectures and migrate existing LLMs with minimal performance loss☆505Jul 14, 2026Updated 2 months ago
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,254Sep 1, 2026Updated 2 weeks ago
- ☆118Updated this week
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆407Jul 10, 2025Updated last year
- MetaAttention: A Unified and Performant Attention Framework Across Hardware Backends(PPoPP'26)☆17Aug 6, 2026Updated last month
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆492Updated this week
- ☆54May 19, 2025Updated last year