[Intel GPU][quant] Refine zero-point memory creation #148640
Conversation
🔗 Helpful Links🧪 See artifacts and rendered test results at hud.pytorch.org/pr/148640
Note: Links to docs will display an error until the docs builds have been completed. ✅ You can merge normally! (5 Unrelated Failures)As of commit 25763ba with merge base e2a0296 ( FLAKY - The following jobs failed but were likely due to flakiness present on trunk:
BROKEN TRUNK - The following job failed but were present on the merge base:👉 Rebase onto the `viable/strict` branch to avoid these failures
UNSTABLE - The following job is marked as unstable, possibly due to flakiness on trunk:
This comment was automatically generated by Dr. CI and updates every 15 minutes. |
|
@pytorchbot rebase |
|
@pytorchbot started a rebase job onto refs/remotes/origin/viable/strict. Check the current status here |
|
Successfully rebased |
|
@pytorchbot 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 |
|
@pytorchbot merge |
|
The merge job was canceled or timed out. This most often happen if two merge requests were issued for the same PR, or if merge job was waiting for more than 6 hours for tests to finish. In later case, please do not hesitate to reissue the merge command |
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 |
Motivation
This PR skips zero-point GPU memory creation when zero-point=0, as it would not be used by oneDNN library. This could help save the 1~3 H2D copy overhead per QLinear/QConv kernel.
Stack from ghstack (oldest at bottom):
cc @jgong5 @mingfeima @XiaobingSuper @sanchitintel @ashokei @jingxu10