Back to Topics Directory
Topic Hub

#flash-attention (5 Repositories)

Ranked open-source repositories tagged with #flash-attention, scored by pull request acceptance likelihood and maintainer engagement velocity.

Topic Avg Merge Rate

32.0%

Avg Review Latency

47.6h

Filter by language

5 repositories tagged #flash-attention

B TierPython 325

xlite-dev/ffpa-attn

Fast and Memory-Efficient Exact Attention (BF16/FP16/FP8/FP4) for Large Headdim, 1.5x~15x speedup over PyTorch SDPA.

96.4%
Merge Rate
9d
First Review
100%
1st-Timers
1
Maintainers
A TierPython 915

NVIDIA/cudnn-frontend

cuDNN Frontend is NVIDIA's modern, open-source entry point to the cuDNN library and a growing collection of high-performance open-source kernels.

63.6%
Merge Rate
11h
First Review
70%
1st-Timers
26
Maintainers
D TierPython 794

NVlabs/rcm

rCM & Causal-rCM: Leading and Unified Algorithms/Infrastructures for Bidirectional/Autoregressive Video Diffusion Distillation at Scale

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierPython 104

Nathanw1014/strix-halo-llamacpp

Performance-tuned llama.cpp for AMD Strix Halo (gfx1151): FA + MoE-prefill fixes with a bundled current Mesa driver. Vulkan and HIP; portable dir, Docker, and distrobox.

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
D TierPython 747

HKUSTDial/flash-sparse-attention

Trainable fast and memory-efficient sparse attention

0.0%
Merge Rate
-
First Review
0%
1st-Timers
0
Maintainers
Best Flash-attention Open Source Repositories & C-Rank™ | GetMerged