Skip to content

Repeerc/flash-attention-v2-RDNA3-minimal

View on GitHub ↗Related repositories →

a simple Flash Attention v2 implementation with ROCM (RDNA3 GPU, roc wmma), mainly used for stable diffusion(ComfyUI) in Windows ZLUDA environments.

active 2024-07-012026-04-09 (UTC)

Complete coverage26,719 / 26,719 hourly files (100%) · 2 absent upstream2023-08-152026-09-01 (UTC)
Events
119
Pushes
41
Pull requests
0
Issues
8
Stars
57
Forks
6

Activity over time

Daily event counts in the loaded window

Line chart, 648 days from 2024-07-01 to 2026-04-09. Pushes: 41 total, peak 8 in a day. Pull requests: 0 total, peak 0 in a day. Issues: 8 total, peak 2 in a day. Comments: 3 total, peak 3 in a day. Stars: 57 total, peak 5 in a day.

  • Pushes
  • Pull requests
  • Issues
  • Comments
  • Stars

Stars, PRs, issues and forks are under-captured in the later part of this window. GH Archive progressively stopped capturing non-push events during 2026 — −95% or worse by the end of the window. Every series here except Pushes fades for that reason, so a decline above reflects the archive, not this repository. Pushes stay reliable throughout, so read them, and the contributor counts derived from them, as the real signal. Data health has the measurements.

Top contributors

Pushes, PRs, issues, reviews and comments — stars and forks excluded, so this is contribution rather than popularity

ContributorContributionsPushesPRsComments
Repeerc434102
feffy3803001
bghira1000
farshadghodsian1000
lahmuller1000
marcussacana1000
Jay197511031000
wangzi76543211000

Recent activity

Latest issues, pull requests and releases

  • Issue#6marcussacana2025-05-06 03:57
    Build Error
  • Issue#5wangzi76543212025-03-01 10:23
    大佬请问一下这SD-Forge可以这个吗?
  • Issue#4Jay197511032025-01-03 03:19
    Is it possible to provide integration with llama.cpp
  • Issue#3lahmuller2024-10-23 13:03
    Memory Access Fault when running certain matrix in WMMA FA!
  • Issue#2feffy3802024-07-11 15:48
    FlashAttentionFunction for SDXL training?
  • Issue comment#2Repeerc2024-07-11 12:27
    FlashAttentionFunction for SDXL training?
  • Issue comment#2feffy3802024-07-11 10:43
    FlashAttentionFunction for SDXL training?
  • Issue comment#2Repeerc2024-07-11 07:39
    FlashAttentionFunction for SDXL training?
  • Issue#2feffy3802024-07-10 18:14
    FlashAttentionFunction for SDXL training?
  • Issue#1farshadghodsian2024-07-10 17:57
    How can I use this Flash Attention Triton implementation with PyTorch+ROCM?
  • Issue#1bghira2024-07-09 15:41
    demo images

Totals cover only the window loaded into ClickHouse and count events, not GitHub's lifetime totals — 57 stars here means stars gained during the window, not the repo's star count.