Conversation
Contributor
There was a problem hiding this comment.
Pull request overview
This PR updates the XPU PR CI workflow to ensure the benchmark step fails immediately when any benchmark script exits non-zero (including crashes), rather than allowing later commands to mask failures and only erroring at a subsequent docker cp step.
Changes:
- Replaces the long
cmd && cmd && ...chain with sequential commands executed underset -eo pipefail. - Ensures
python3 bench_*.py 2>&1 | tee ...propagates failures correctly within the benchmark step.
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
sunjiweiswift
approved these changes
Aug 26, 2026
arathi-hlab
approved these changes
Aug 26, 2026
…util copy logs A missing && in the long pipefail chain let later benches still run, so the step stayed green and the job only failed on docker cp of a log that was never written.
4 tasks
This branch has not been deployed
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Summary
Run Sglang Kernel Benchmarksused a longcmd | tee log && ...chain. Two missing&&turned later benches into a new bash statement, so a crashing bench (e.g.bench_flash_attn.pyin [Attention] support softmax lse #330) did not fail that step.Copy logs from container(docker cp fused_moe.log), which looks like infra rather than a kernel regression.set -eo pipefailso a non-zeropython3 bench_*.py | teefails this step. Adding a new bench without&&cannot hide a failure again.