Repository navigation
[AMD] MiniMax-M3.1-Flash MI355X vLLM: latest nightly image and merged optimization flags / [AMD] MiniMax-M3.1-Flash MI355X vLLM:最新 nightly 镜像与已合入优化的开关 #4866
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
+36
−34
Merged
Changes from all commits
Commits
Show all changes
7 commits
Select commit
Hold shift + click to select a range
dd65c35
[AMD] MiniMax-M3.1-Flash MI355X vLLM: latest nightly image and merged…
Fangzhou-Ai 6aec58e
Link the performance changelog entry to this PR
Fangzhou-Ai ce4079c
Drop INT4 quick all-reduce: the nightly image's AITER lacks QuickAllR…
Fangzhou-Ai 19a9961
Merge branch 'main' into m31-mi355x-vllm-nightly-stack
chunfangamd f54e244
Merge branch 'main' into m31-mi355x-vllm-nightly-stack
chunfangamd 31d9b00
Merge branch 'main' into m31-mi355x-vllm-nightly-stack
chunfangamd 92fb9db
Merge branch 'main' into m31-mi355x-vllm-nightly-stack
chunfangamd 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
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.
🟡 nit (optional): The rewritten c16-c32 section comment is a header describing an override, which AGENTS.md's comment rules forbid. It also cites a past result ("a coarse list makes decode about 10% slower"). Separately, line 90 is left as an orphaned fragment: "8192-token prefill steps on the V1 runner." Fix: cut the header to a one-line reason on the
compilation-configline, and delete or complete the line 90 fragment.Why this was flagged
AGENTS.md:56-58 says: no header comments describing an override or section, no past results, and only short technical reasons tied to a specific line. The diff rewrites the comment above
zip_override_tp4_dspark7(agentic.yaml:111-116) into a six-line override description. That description includes the measured "about 10% slower" result and narrates the alias behaviour. The DBO edit at agentic.yaml:90 left the sentence fragment "8192-token prefill steps on the V1 runner.", which no longer explains anything. This is not a runtime issue; it is a convention violation the diff introduces.Verification: AGENTS.md:54-58 says "No header comments describing a file, topology, config, recipe, override, or section" and "No history: ... or past results". The diff rewrites the section comment at agentic.yaml:111-116 into a six-line description of the override. At agentic.yaml:90 it leaves a sentence fragment with no subject. It does not change how anything runs.