Fast and Memory-Efficient Exact Attention (BF16/FP16/FP8/FP4) for Large Headdim, 1.5x~15x speedup over PyTorch SDPA.
☆329Aug 31, 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.☆158May 10, 2025Updated last year
- An experimental communicating attention kernel based on DeepEP.☆34Jul 29, 2025Updated last year
- DeeperGEMM: crazy optimized version☆85May 5, 2025Updated last year
- Some funny cute/cuteDSL code snippets☆34Mar 2, 2026Updated 5 months ago
- Accelerating MoE with IO and Tile-aware Optimizations☆752Updated 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.
- High Performance LLM Inference Operator Library☆1,138Updated this week
- Distributed Compiler and Optimized Parallel Kernels☆1,530Aug 12, 2026Updated 2 weeks ago
- High performance RMSNorm Implement by using SM Core Storage(Registers and Shared Memory)☆31Jan 22, 2026Updated 7 months ago
- Kernels, of the mega variety :)☆815May 26, 2026Updated 3 months ago
- A lightweight design for computation-communication overlap.☆245Jan 20, 2026Updated 7 months ago
- ☆62Feb 24, 2026Updated 6 months ago
- FlashInfer: Kernel Library for LLM Serving☆6,298Updated this week
- ☆272Jul 11, 2024Updated 2 years ago
- A Quirky Assortment of CuTe Kernels☆1,135Updated 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.
- Distributed MoE in a Single Kernel [NeurIPS '25]☆288May 5, 2026Updated 3 months ago
- Examples of CUDA implementations by Cutlass CuTe☆281Jul 1, 2025Updated last year
- Tilus is a tile-level kernel programming language with explicit control over shared memory and registers.☆490Aug 17, 2026Updated 2 weeks ago
- Modern CUDA Learn Notes with PyTorch for Beginners, 200+ CUDA Kernels, Tensor Cores, HGEMM, FA-2 MMA.☆11,862Updated this week
- A fast communication-overlapping library for tensor/expert parallelism on GPUs.☆1,357Aug 28, 2025Updated last year
- Implement Flash Attention using Cute.☆111Dec 17, 2024Updated last year
- Official repository Flash Local Linear Attention☆39May 28, 2026Updated 3 months ago
- FlashKDA: high-performance Kimi Delta Attention kernels☆1,240Jul 30, 2026Updated last month
- ☆32Jul 2, 2025Updated last year
- 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.
- A PyTorch-native inference engine with cache, parallelism, quantization and cpu offload for DiTs.☆1,262Updated this week
- ☆65Apr 26, 2025Updated last year
- NVIDIA cuTile learn☆167Dec 9, 2025Updated 8 months ago
- CUDA kernels for linear attention variants, written in CuTe DSL and CUTLASS C++.☆543Updated this week
- A Easy-to-understand TensorOp Matmul Tutorial☆452Mar 5, 2026Updated 5 months ago
- flash attention tutorial written in python, triton, cuda, cutlass☆532Jan 20, 2026Updated 7 months ago
- Perplexity GPU Kernels☆604Nov 7, 2025Updated 9 months ago
- Low overhead tracing library and trace visualizer for pipelined CUDA kernels☆135Jul 29, 2026Updated last month
- Benchmark tests supporting the TiledCUDA library.☆19Nov 19, 2024Updated last year
- 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.
- A Distributed Attention Towards Linear Scalability for Ultra-Long Context, Heterogeneous Data Training☆929Updated this week
- Several optimization methods of half-precision general matrix multiplication (HGEMM) using tensor core with WMMA API and MMA PTX instruct…☆567Sep 8, 2024Updated last year
- ☆54May 19, 2025Updated last year
- A collection of specialized agent skills for AI infrastructure development, enabling Claude Code to write, optimize, and debug high-perfo…☆144Jul 9, 2026Updated last month
- ☆384Jan 28, 2026Updated 7 months ago
- how to optimize some algorithm in cuda.☆3,239Updated this week
- ☆253Nov 19, 2025Updated 9 months ago