Skip to content

modulated_rms_norm: add cuTile kernel & feat(ops): add attention_variant kernels (Triton + cuTile) & other updates - #186

Open
hannahli-nv wants to merge 4 commits into
mainfrom
tilegym_update
Open

modulated_rms_norm: add cuTile kernel & feat(ops): add attention_variant kernels (Triton + cuTile) & other updates#186
hannahli-nv wants to merge 4 commits into
mainfrom
tilegym_update

Conversation

@hannahli-nv

@hannahli-nv hannahli-nv commented Aug 19, 2026

Copy link
Copy Markdown
Collaborator

Description

Update codes.

This PR contains 4 new commit(s).

Commits included:

9a6a6a0 fix(benchmark): pick kernel_name from timed non-helper kernels
0ababdd Tile C++ FMHA perf matching
b409f91 feat(ops): add attention_variant kernels (Triton + cuTile)
19830ee modulated_rms_norm: add cuTile kernel

CI Configuration

config:
  build: true
  # valid options are "ops" and "benchmark"
  test: []

Checklist

  • Code formatted and imports sorted via repo specifications (./format.sh)
  • Documentation updated (if needed)
  • CI configuration reviewed

@copy-pr-bot

copy-pr-bot Bot commented Aug 19, 2026

Copy link
Copy Markdown

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

yifeis-nv and others added 3 commits August 19, 2026 08:40
Co-authored-by: Hannah Li <hanli@nvidia.com>
Co-authored-by: Yinuo Liu <yinuol@nvidia.com>
Co-authored-by: Jinman Xie <jinmanx@nvidia.com>
Co-authored-by: Zhengyi Zhang <zhengyiz@nvidia.com>
Co-authored-by: Zhiwei Fang <zhiweif@nvidia.com>
Co-authored-by: Feiwen Zhu <mzhu@nvidia.com>
@hannahli-nv hannahli-nv changed the title modulated_rms_norm: add cuTile kernel modulated_rms_norm: add cuTile kernel & feat(ops): add attention_variant kernels (Triton + cuTile) & other updates Aug 20, 2026
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.

5 participants