Skip to content

[moe][perf] tune qwen235b a16w16 moe config#3298

Open
lalala-sh wants to merge 1 commit into
mainfrom
wjx/tued_bf16_moe_qwen235b
Open

[moe][perf] tune qwen235b a16w16 moe config#3298
lalala-sh wants to merge 1 commit into
mainfrom
wjx/tued_bf16_moe_qwen235b

Conversation

@lalala-sh
Copy link
Copy Markdown
Contributor

@lalala-sh lalala-sh commented May 21, 2026

Motivation

Tune qwen235b a16w16 moe config

Technical Details

Test Plan

Test Result

Submission Checklist

@lalala-sh lalala-sh requested a review from a team May 21, 2026 07:56
@github-actions
Copy link
Copy Markdown
Contributor

🏷️ CI Guide

Runs automatically on every PR:

  • ✅ Pre-checks (submodule verification, code formatting)
  • ✅ Aiter op tests (gfx942 + gfx950)
  • ✅ Triton tests on MI35X (only when aiter/ops/triton/** or related paths are changed)

Extended tests (opt-in via labels):

Label Tests
ci:triton-300x Run an additional Triton test job on MI300X in PRs; main branch always runs both MI35X and MI300X
ci:sglang SGLang integration tests: DeepSeek-R1-MXFP4 accuracy, Qwen 3.5 accuracy
ci:atom ATOM benchmark: DeepSeek-R1-0528, GPT-OSS-120B
ci:atom_full ATOM accuracy suite for PR and main models from ATOM models_accuracy.json
ci:vllm vLLM benchmark: GPT-OSS-120B, DeepSeek-R1-0528, Kimi-K2.5
ci:all All standard extended tests (excludes ci:atom_full)

Only add ci:atom_full for FlyDSL or Triton upgrades.
Add labels via the sidebar or gh pr edit 3298 --add-label <label>

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant