ci: use trimmed latency and pinned feed envs#186
Merged
ronnie-devtech merged 7 commits intoMooreThreads:mainfrom Apr 23, 2026
Merged
ci: use trimmed latency and pinned feed envs#186ronnie-devtech merged 7 commits intoMooreThreads:mainfrom
ronnie-devtech merged 7 commits intoMooreThreads:mainfrom
Conversation
weloMThreads
changed the title
tngchien
pushed a commit
to tngchien/tensorflow_musa_extension
that referenced
this pull request
Apr 24, 2026
* ci: use trimmed latency and pinned feed envs * ci: pin pruned graph batch size * ci: cancel superseded PR validation runs * ci: stop passing duplicate pruned graph batch flag * ci: tune tf test model runner args * ci: update workflow naming and notifications * ci: test PR merge commit
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
MUSA_PINNED_FEED=1andMUSA_PINNED_H2D_ON_COMPUTE_STREAM=1to the BD model perf runs in CItrimmed_avg_ms, with fallback toaverage_time_msfor compatibility with older runner outputWhy
musa_run_pb_graph.pysupports pinned-feed execution and reports a trimmed latency averageValidation
git diff --check -- .github/workflows/pr-validation.yml