[CUDA][cuBLAS] Only xFail addmm with reduced precision reductions on non-RTX skus#165379
[CUDA][cuBLAS] Only xFail addmm with reduced precision reductions on non-RTX skus#165379
xFail addmm with reduced precision reductions on non-RTX skus#165379Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/165379
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (2 Unrelated Failures)As of commit 9395619 with merge base f368345 ( FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
Skylion007
left a comment
There was a problem hiding this comment.
Huh, can we raise the tolerance just for datacenter GPUs?
|
Yeah, I expect the RTX-skus to use more Ampere style kernels due to tensor core differences. |
|
@pytorchmergebot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
Merge failedReason: 1 jobs have failed, first few of them are: trunk / linux-jammy-py3-clang12-executorch / test (executorch, 1, 1, linux.2xlarge) Details for Dev Infra teamRaised by workflow job |
|
@pytorchmergebot merge |
Merge startedYour change will be merged once all checks pass (ETA 0-4 Hours). Learn more about merging in the wiki. Questions? Feedback? Please reach out to the PyTorch DevX Team |
… on non-RTX skus (pytorch#165379) RTX Blackwells don't behave quite like their datacenter counterparts here Pull Request resolved: pytorch#165379 Approved by: https://github.com/Skylion007
… on non-RTX skus (pytorch#165379) RTX Blackwells don't behave quite like their datacenter counterparts here Pull Request resolved: pytorch#165379 Approved by: https://github.com/Skylion007
RTX Blackwells don't behave quite like their datacenter counterparts here
cc @ptrblck @msaroufim @jerryzh168 @mruberry @csarofeen @xwang233