Skip to content

Aiterker 112 asm ptl1 - #4348

Open
JohnNikolay84 wants to merge 16 commits into
mainfrom
AITERKER-112-ASM-PTL1
Open

Aiterker 112 asm ptl1#4348
JohnNikolay84 wants to merge 16 commits into
mainfrom
AITERKER-112-ASM-PTL1

Conversation

@JohnNikolay84

Copy link
Copy Markdown
Contributor

Motivation

This branch contains ps64 kernel for HY30 model designed to run on GPU with mfma/valu overlap.

Technical Details

Test Plan

Test Result

Submission Checklist

@JohnNikolay84 JohnNikolay84 self-assigned this Jul 23, 2026
@JohnNikolay84
JohnNikolay84 requested a review from a team July 23, 2026 08:30
@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 4348 --add-label <label>

print(" " + " ".join(f"{int(i)}:{float(v):.3f}" for v, i in zip(top.values, top.indices)))
print(f" [ROW_DIAG] rows<pos mean={rn[:pos].mean():.4f} rows>=pos mean={rn[pos:].mean():.4f}")
w = int(top.indices[0])
of = out_f[w].reshape(-1); orf = out_ref[w].reshape(-1)

Copy link
Copy Markdown
Contributor

Choose a reason for hiding this comment

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

⚠️ [ruff] <E702> reported by reviewdog 🐶
Multiple statements on one line (semicolon)

@zufayu
zufayu requested a review from amd-ruitang3 July 24, 2026 01:32
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.

1 participant