Repository navigation
fix(synthetic-acceptance): drop Kimi vLLM parsers on synthetic throughput points #4840
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Merged
Merged
Changes from all commits
Commits
Show all changes
3 commits
Select commit
Hold shift + click to select a range
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
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
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
Oops, something went wrong.
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Outdated suggestions cannot be applied.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.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🔴 Kimi vLLM synthetic throughput benchmarks now run without their parsers, but no perf-changelog entry is added, so the re-run the PR describes won't be scheduled. CONTRIBUTING.md:30 requires a new entry at the end of
inferencex-e2e/perf-changelog.yamlfor any change to what a benchmark runs. The diff only touches synthetic_acceptance.py and its test. Fix: append one entry listing every affected Kimi vLLM synthetic-acceptance config key, includingkimik3.1-fp4-b300-vllm-agentic-dspark.python -m infx.matrix.changed --base origin/mainlists them.Why this was flagged
synthetic_acceptance.py:304-307 now adds
--unset roles.<name>.args.{enable-auto-tool-choice,tool-call-parser,reasoning-parser}for every vLLM worker whose MODEL_PREFIX starts with "kimi" and that receives a synthetic acceptance length. That changes the server command, and the PR's own numbers show it changes ITL and error counts. CONTRIBUTING.md:30 says such a PR MUST append a perf-changelog.yaml entry for the affected config keys, and the changelog diff is what selects the sweep.git diff --statshows only two changed files and no perf-changelog.yaml. Sokimik3.1-fp4-b300-vllm-agentic-dspark(nvidia-master.yaml:5727) is not re-run. Its published ITL and interactivity stay at the 17–26% optimistic values from the parsers-on run until some unrelated changelog entry triggers that key.Verification: The diff touches only
inferencex-e2e/infx/srt_slurm/synthetic_acceptance.pyand its test, andperf-changelog.yamlis unchanged. Lines 304-307 add--unset {prefix}.args.{key}for the parsers whenMODEL_PREFIXstarts with "kimi".infx.matrix.changeddoes not see script changes like this one, so without an entry no sweep or result collection is triggered.