Skip to content

[TRITON] Moe a8w4 gluon gfx1250#2228

Open
lburzawa wants to merge 4 commits intomainfrom
moe_gluon_gfx1250_to_main
Open

[TRITON] Moe a8w4 gluon gfx1250#2228
lburzawa wants to merge 4 commits intomainfrom
moe_gluon_gfx1250_to_main

Conversation

@lburzawa
Copy link
Contributor

@lburzawa lburzawa commented Mar 9, 2026

Motivation

Support MOE a8w4 on gfx1250 using gluon.

Technical Details

  • moe a8w4 kernel in gluon for gfx1250
  • Rewrite moe a8w4 wrapper to support both triton and gluon kernels

Test Plan

UTs on FFM and IR/asm analysis

Test Result

UTs pass on 350 and 450

Submission Checklist

@lburzawa lburzawa requested a review from a team March 9, 2026 20:38
@github-actions
Copy link
Contributor

github-actions bot commented Mar 9, 2026

🏷️ CI Guide

Runs automatically on every PR:

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

Extended tests (opt-in via labels):

Label Tests
ci:sglang SGLang integration tests
ci:atom ATOM benchmark (DeepSeek-R1 + GPT-OSS)
ci:multi-gpu Multi-GPU op tests (8 GPU)
ci:vllm vLLM benchmark
ci:all All of the above

Add labels via the sidebar or gh pr edit 2228 --add-label <label>

lburzawa and others added 2 commits March 9, 2026 13:40
Co-authored-by: github-actions[bot] <41898282+github-actions[bot]@users.noreply.github.com>
Copy link
Contributor

@azaidy azaidy left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM!

@azaidy azaidy requested a review from vgokhale March 11, 2026 17:32
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.

2 participants