Skip to content

[Triton] [ATOM] DSV4 mxfp8 GEMM#3286

Draft
k50112113 wants to merge 9 commits into
mainfrom
shaoclee/alizaidy-dsv4-mxfp8_gemm
Draft

[Triton] [ATOM] DSV4 mxfp8 GEMM#3286
k50112113 wants to merge 9 commits into
mainfrom
shaoclee/alizaidy-dsv4-mxfp8_gemm

Conversation

@k50112113
Copy link
Copy Markdown
Contributor

@k50112113 k50112113 commented May 20, 2026

This PR adds MXFP8 GEMM variants by @azaidy

@k50112113 k50112113 marked this pull request as ready for review May 20, 2026 15:07
@k50112113 k50112113 requested a review from a team May 20, 2026 15:07
@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 3286 --add-label <label>

k50112113 added 2 commits May 21, 2026 10:22
* add fused_gemm_a16w16_copy_x, remove near-moe torch.to and torch.zeros kernels

* tunning

* revert fill(0) change
@k50112113 k50112113 marked this pull request as draft May 21, 2026 22:18
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