Add aiter bias moe support in gpt-oss mxfp4 model#17735
Merged
HaiShaw merged 4 commits intosgl-project:mainfrom Jan 29, 2026
Merged
Add aiter bias moe support in gpt-oss mxfp4 model#17735HaiShaw merged 4 commits intosgl-project:mainfrom
HaiShaw merged 4 commits intosgl-project:mainfrom
Conversation
Contributor
|
Warning You have reached your daily quota limit. Please wait up to 24 hours and I will start processing your requests again! |
Collaborator
|
/tag-and-rerun-ci |
HaiShaw
approved these changes
Jan 29, 2026
charlesHsuGG
pushed a commit
to charlesHsuGG/sglang
that referenced
this pull request
Jan 30, 2026
Co-authored-by: wunhuang <wunhuang@amd.com>
Chen-0210
pushed a commit
to Chen-0210/sglang
that referenced
this pull request
Jan 30, 2026
Co-authored-by: wunhuang <wunhuang@amd.com>
sfiisf
pushed a commit
to sfiisf/sglang
that referenced
this pull request
Feb 5, 2026
Co-authored-by: wunhuang <wunhuang@amd.com>
Johnsonms
pushed a commit
to Johnsonms/sglang
that referenced
this pull request
Feb 14, 2026
Co-authored-by: wunhuang <wunhuang@amd.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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Motivation
Optimized MoE performance in ROCm platform when running the gpt-oss mxfp4 model
Modifications
mxfp4.py => Add aiter path for weight processing and use aiter fusedMoe function to handle MoE op
Accuracy Tests
sglang# python3 benchmark/gsm8k/bench_sglang.py --num-questions 2000 --parallel 2000 --port 8000 100%|█████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████████| 1319/1319 [00:44<00:00, 29.78it/s] Accuracy: 0.882 Invalid: 0.007 Latency: 44.526 s Output throughput: 9263.069 token/sBenchmarking and Profiling
Checklist
Review Process
/tag-run-ci-label,/rerun-failed-ci,/tag-and-rerun-ci