FFPA: Extend FlashAttention-2 with Split-D, ~O(1) SRAM complexity for large headdim, 1.8x~3x↑🎉 vs SDPA.
☆276Apr 29, 2026Updated this week
Alternatives and similar repositories for ffpa-attn
Users that are interested in ffpa-attn are comparing it to the libraries listed below. We may earn a commission when you buy through links labeled 'Ad' on this page.
Sorting:
- ⚡️Write HGEMM from scratch using Tensor Cores with WMMA, MMA and CuTe API, Achieve Peak⚡️ Performance.☆151May 10, 2025Updated 11 months ago
- ☆66Apr 26, 2025Updated last year
- Quantized Attention on GPU☆44Nov 22, 2024Updated last year
- Distributed Compiler based on Triton for Parallel Systems☆1,420Apr 22, 2026Updated last week
- DeepGEMM: clean and efficient FP8 GEMM kernels with fine-grained scaling☆22Updated this week
- 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.
- TileFusion is an experimental C++ macro kernel template library that elevates the abstraction level in CUDA C for tile processing.☆108Jun 28, 2025Updated 10 months ago
- ☆264Jul 11, 2024Updated last year
- flash attention tutorial written in python, triton, cuda, cutlass☆506Jan 20, 2026Updated 3 months ago
- We invite you to visit and follow our new repository at https://github.com/microsoft/TileFusion. TiledCUDA is a highly efficient kernel …☆193Jan 28, 2025Updated last year
- A Easy-to-understand TensorOp Matmul Tutorial☆428Mar 5, 2026Updated last month
- 📚LeetCUDA: Modern CUDA Learn Notes with PyTorch for Beginners🐑, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.🎉☆10,825Apr 20, 2026Updated last week
- ☆52May 19, 2025Updated 11 months ago
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,295Aug 28, 2025Updated 8 months ago
- FlashInfer: Kernel Library for LLM Serving☆5,544Updated this week
- 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.
- DeeperGEMM: crazy optimized version☆86May 5, 2025Updated 11 months ago
- Framework to reduce autotune overhead to zero for well known deployments.☆99Sep 19, 2025Updated 7 months ago
- Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruct…☆543Sep 8, 2024Updated last year
- 使用 cutlass 仓库在 ada 架构上实现 fp8 的 flash attention☆81Aug 12, 2024Updated last year
- A lightweight design for computation-communication overlap.☆229Jan 20, 2026Updated 3 months ago
- ☆20Sep 28, 2024Updated last year
- Fast low-bit matmul kernels in Triton☆445Apr 24, 2026Updated last week
- how to optimize some algorithm in cuda.☆2,952Apr 22, 2026Updated last week
- ☆65Feb 15, 2026Updated 2 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.
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated 9 months ago
- Domain-specific language designed to streamline the development of high-performance GPU/CPU/Accelerators kernels☆5,928Updated this week
- An efficient GPU support for LLM inference with x-bit quantization (e.g. FP6,FP5).☆280Jul 16, 2025Updated 9 months ago
- ☆119May 19, 2025Updated 11 months ago
- Efficient LLM Inference over Long Sequences☆394Jun 25, 2025Updated 10 months ago
- Kernels, of the mega variety :)☆714Updated this week
- A throughput-oriented high-performance serving framework for LLMs☆954Mar 29, 2026Updated last month
- FlagGems is an operator library for large language models implemented in the Triton Language.☆972Updated this week
- ☆33Feb 3, 2025Updated last year
- 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.
- A collection of memory efficient attention operators implemented in the Triton language.☆290Jun 5, 2024Updated last year
- Multiple GEMM operators are constructed with cutlass to support LLM inference.☆20Aug 3, 2025Updated 9 months ago
- Implement Flash Attention using Cute.☆106Dec 17, 2024Updated last year
- Efficient triton implementation of Native Sparse Attention.☆275May 23, 2025Updated 11 months ago
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆483Updated this week
- ☆150Jan 9, 2025Updated last year
- 📚A curated list of Awesome LLM/VLM Inference Papers with Codes: Flash-Attention, Paged-Attention, WINT8/4, Parallelism, etc.🎉☆5,185Apr 20, 2026Updated last week