BetaRare
tspeterkim/flash-attention-minimal
Flash Attention in ~100 lines of CUDA (forward pass only)
- Owner
- tspeterkim (personal account)
- Stars
- Stars: 1,203
- Forks
- Forks: 121
- Language
- Cuda
- License
- Apache-2.0
- Created
- 2024
- Tier
- Beta (700 to 1,999 ★) What this tier means
More repos by tspeterkim
All 3 repos by tspeterkim- tspeterkim/insta-chatStars: 238HTMLPrototype
- tspeterkim/paged-attention-minimalStars: 152PythonPrototype
Nearby in Cuda
All Cuda repos- MoonshotAI/FlashKDAStars: 1,295CudaBeta
- PacktPublishing/Learn-CUDA-ProgrammingStars: 1,268CudaBeta
- thu-ml/SpargeAttnStars: 1,266CudaBeta
- antonmks/AlenkaStars: 1,166CudaBeta
- Tongkaio/CUDA_Kernel_SamplesStars: 1,143CudaBeta
- NVIDIA/cuoptStars: 1,094CudaBeta