frozenleaves/pytorch
1
0
Fork 0
mirror of https://github.com/pytorch/pytorch.git synced 2025-10-20 21:14:14 +08:00
Code Issues Packages Projects Releases Wiki Activity

[triton] update 3.5 pin to bbb06c0334a6772b92d24bde54956e675c8c6604 (#163382)

Browse Source 
Includes:
* https://github.com/triton-lang/triton/pull/8211 to work around a PTXAS bug that was causing 03-matrix-multiplication tutorial matmuls to underperform due to excessive WGMMA waits
* https://github.com/triton-lang/triton/pull/8157 to fix a convert_layout bug

Verified that this passes Triton CI in https://github.com/pytorch/pytorch/pull/159158 and improves gemm perf (see https://github.com/pytorch/pytorch/issues/159704)
Pull Request resolved: https://github.com/pytorch/pytorch/pull/163382
Approved by: https://github.com/Camyll, https://github.com/atalman
This commit is contained in:
David Berard
2025-09-19 16:06:35 -07:00
committed by PyTorch MergeBot
parent 6f9aef5fef
commit d0086708dd
1 changed files with 1 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
.ci/docker/ci_commit_pins/triton.txt
View File

@ -1 +1 @@
5ae38bdb0dc066c5823e34dc9797afb9de42c866
bbb06c0334a6772b92d24bde54956e675c8c6604