Fast and memory-efficient exact attention
☆122May 21, 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☆5,666Updated this week
- FlashTile is a CUDA Tile IR compiler that is compatible with NVIDIA's tileiras, targeting SM70 through SM121 NVIDIA GPUs.☆60Feb 6, 2026Updated 3 months ago
- CUDA Templates for Linear Algebra Subroutines☆101Apr 25, 2024Updated 2 years ago
- ☆19Mar 4, 2025Updated last year
- KV cache store for distributed LLM inference☆419Nov 13, 2025Updated 6 months ago
- 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.
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆155May 10, 2025Updated last year
- performance engineering☆31Jul 11, 2024Updated last year
- ☆11Aug 23, 2023Updated 2 years ago
- A tiny yet powerful LLM inference system tailored for researching purpose. vLLM-equivalent performance with only 2k lines of code (2% of …☆330Jun 10, 2025Updated 11 months ago
- A Triton-only attention backend for vLLM☆25Mar 17, 2026Updated 2 months ago
- ☆18Jan 4, 2024Updated 2 years ago
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆30Jan 22, 2026Updated 4 months ago
- RTP-LLM: Alibaba's high-performance LLM inference engine for diverse applications.☆1,119May 20, 2026Updated last week
- 1-Click AI Models by DigitalOcean Gradient • AdDeploy popular AI models on DigitalOcean Gradient GPU virtual machines with just a single click. Zero configuration with optimized deployments.
- ☆157Mar 4, 2025Updated last year
- vLLM plugin for RBLN NPU☆49Updated this week
- Benchmark SGLang on SLURM☆24Apr 20, 2026Updated last month
- High-performance LLM operator library built on TileLang.☆124May 20, 2026Updated last week
- ☆33Feb 3, 2025Updated last year
- Mooncake is the serving platform for Kimi, a leading LLM service provided by Moonshot AI.☆5,401Updated this week
- High-performance safetensors model loader☆143May 19, 2026Updated last week
- A sparse attention kernel supporting mix sparse patterns☆516Jan 18, 2026Updated 4 months ago
- [ICML 2024] Quest: Query-Aware Sparsity for Efficient Long-Context LLM Inference☆386Jul 10, 2025Updated 10 months ago
- Simple, predictable pricing with DigitalOcean hosting • AdAlways know what you'll pay with monthly caps and flat pricing. Enterprise-grade infrastructure trusted by 600k+ customers.
- Code for paper: [ICLR2025 Oral] FlexPrefill: A Context-Aware Sparse Attention Mechanism for Efficient Long-Sequence Inference☆168Oct 13, 2025Updated 7 months ago
- 基于语义的中文文本关键词提取算法☆20Mar 24, 2021Updated 5 years ago
- 3rd party dependencies for DALI project☆11Updated this week
- study of cutlass☆22Nov 10, 2024Updated last year
- Demo for Qwen2.5-VL-3B-Instruct on Axera device.☆16Sep 3, 2025Updated 8 months ago
- Disaggregated serving system for Large Language Models (LLMs).☆815Apr 6, 2025Updated last year
- triton for dsa☆65May 20, 2026Updated last week
- Efficient and easy multi-instance LLM serving☆551Mar 12, 2026Updated 2 months ago
- ☆30May 31, 2025Updated 11 months ago
- GPU virtual machines on DigitalOcean Gradient AI • AdGet to production fast with high-performance AMD and NVIDIA GPUs you can spin up in seconds. The definition of operational simplicity.
- A collection of models for TensorFlow Go☆12May 29, 2022Updated 3 years ago
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆24May 20, 2026Updated last week
- Official repository of "Distort, Distract, Decode: Instruction-Tuned Model Can Refine its Response from Noisy Instructions", ICLR 2024 Sp…☆21Mar 7, 2024Updated 2 years ago
- A curated list for Efficient Large Language Models☆11Mar 25, 2024Updated 2 years ago
- ☆22May 5, 2025Updated last year
- 🤖FFPA: Extends FlashAttention-2 via Split-D for large headdims, 1.5x~3×↑🎉 vs SDPA, up to 430T🎉 on H200.☆299May 20, 2026Updated last week
- ☆20Dec 24, 2024Updated last year