Skip to content

Jm/bio 713 mxfp8 enum member#285

Merged
jomitchellnv merged 2 commits into
mainfrom
jm/bio-713-mxfp8-enum-member
Jun 4, 2026
Merged

Jm/bio 713 mxfp8 enum member#285
jomitchellnv merged 2 commits into
mainfrom
jm/bio-713-mxfp8-enum-member

Conversation

@jomitchellnv

Copy link
Copy Markdown
Collaborator

Description

Closes #

Checklist

Please confirm the following before requesting review. PRs that do not meet these requirements cannot be merged. See CONTRIBUTING.md for the full contribution rules.

Contribution rules

  • I have read and am adhering to the Contribution Rules.
  • An issue was filed and approved by the NVIDIA team before this PR.
  • I have installed and run pre-commit locally (pip install pre-commit && pre-commit install).
  • This PR addresses a single concern and avoids unnecessary complexity or commented-out code.
  • If this PR is a work in progress, the title is prefixed with [WIP].

Sign-off (DCO)

Per Signing Your Work, every commit in this PR must be signed off with git commit -s (appending Signed-off-by: Your Name <your@email.com>). PRs containing unsigned commits will not be accepted.

  • All commits in this PR are signed off (git commit -s).
  • By signing off, I certify that I have the right to submit this contribution under the project's open source license, in accordance with the Developer Certificate of Origin v1.1.

jomitchellnv and others added 2 commits June 3, 2026 11:37
Mirror MXFP8/BFLOAT16 into the fallback TriMulPrecision enum so
precision=TriMulPrecision.MXFP8 resolves whether or not the
cuequivariance_ops_torch backend is installed. Document the MXFP8
option in the triangle_multiplicative_update docstring as opt-in,
inference-only, seq % 32 == 0, Blackwell-only (cc >= 10.0), with
transparent bf16 fallback. Add frontend tests: an always-on enum-member
check and a GPU-guarded MXFP8 inference exercise (string + enum paths).

Default stays precision=None (off); MXFP8 backward is not yet implemented.

Signed-off-by: Jonathan Mitchell <jomitchell@nvidia.com>
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
Carry forward the BIO-713 review change: the fallback TriMulPrecision
enum mirrors the backend sentinels, which moved from -1000/-1001 to the
sequential enum values 4/5. Update the enum-member test assertions to match.

Signed-off-by: Jonathan Mitchell <jomitchell@nvidia.com>
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
@copy-pr-bot

copy-pr-bot Bot commented Jun 3, 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.

@jomitchellnv jomitchellnv requested a review from trvachov June 3, 2026 19:07
@jomitchellnv jomitchellnv merged commit ff0ce84 into main Jun 4, 2026
18 checks passed
jomitchellnv added a commit that referenced this pull request Jun 8, 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.

2 participants