[AMD][MI355X] update model for gpt-oss #1638
Draft
ukannika wants to merge 2 commits into
Draft
Conversation
ukannika
requested review from
1am9trash,
billishyahao,
chunfangamd,
seungrokj and
yctseng0211
as code owners
![claude[bot]](https://avatars.githubusercontent.com/in/1236702?s=60&v=4){kind=small}
Collaborator
|
/sweep test-config --config-files .github/configs/amd-master.yaml --config-keys gptoss-fp4-mi355x-vllm |
Contributor
|
@chunfangamd Kicking off a sweep. Run: https://github.com/SemiAnalysisAI/InferenceX/actions/runs/26845310867 |
chunfangamd
force-pushed
the
amd/update_gpt_oss_mi355x_config
branch
from
decdda7 to
fd1594b
Compare
Record the GPT-OSS MI355X vLLM model update (amd/gpt-oss-120b-w-mxfp4-a-fp8 -> openai/gpt-oss-120b). Co-authored-by: Cursor <cursoragent@cursor.com>
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Switch moe backend to CK to leverage the benefits from this PR.
vllm-project/vllm#42098
Note
Medium Risk
Changes which weights the MI355X GPT-OSS sweep loads and serves; throughput and eval numbers may shift versus the prior AMD checkpoint even though sweep geometry is unchanged.
Overview
Switches the MI355X GPT-OSS FP4 vLLM benchmark (
gptoss-fp4-mi355x-vllm) from the AMD MXFP4 checkpointamd/gpt-oss-120b-w-mxfp4-a-fp8to the upstream Hugging Face weightsopenai/gpt-oss-120b, while keeping the same image (vllm/vllm-openai-rocm:v0.22.0), runner, precision label, and fixed-seq-len TP/concurrency sweep.Documents the change in
perf-changelog.yamlfor config keygptoss-fp4-mi355x-vllm(PR #1638). The PR description ties this to using the CK MoE backend in vLLM (vllm#42098); that behavior is not altered in this diff—only the configuredmodelid and changelog entry change.Reviewed by Cursor Bugbot for commit a30921f. Bugbot is set up for automated code reviews on this repo. Configure here.