Skip to content

Issues: ROCm/aotriton

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

11 Open 10 Closed
11 Open 10 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

[Issue]: The reason why the bwd kernel is not fused
#62 opened Dec 25, 2024 by lzc17
[Issue]: aotriton depends on downloading CUDART to build
#58 opened Dec 8, 2024 by LunNova
1
[Documentation]: large bf16 inputs leads to nan
#54 opened Nov 7, 2024 by xinyazhang
[Documentation]: Forward kernel returns NaN when inputs are irregular (including causal) and sm_scale is 0
#47 opened Oct 7, 2024 by xinyazhang
1
[Documentation]: The overall tuning idea of ​​aotriton
#38 opened Jul 26, 2024 by hubotao1
6
[Perf] Is it possible that the kernels wrapped with AOT have the similar performance comparing with the original ones?
#37 opened Jul 24, 2024 by xinji1
1
[Issues]: The Gap between AOT and JIT Triton on Flash Attention kernel
#34 opened Jun 28, 2024 by jinsong-mao
[Issue]: failed to run the tune_flash.py
#32 opened Jun 17, 2024 by jinsong-mao
13
[Feature]: CDNA1 Support
#27 opened May 24, 2024 by IMbackK
[Feature]: Fix the mandatory boundary_check when loading bias tensor
#17 opened Apr 22, 2024 by xinyazhang
[Documentation]: Shall we modify the configurations in v2python for the other kernels?
#12 opened Apr 2, 2024 by xinji1
5
ProTip! Exclude everything labeled bug with -label:bug.