Skip to content

[Bug] [patch] GPT-OSS low MXFP8 speedup comparing to BF16 #3389

@dingqingy-nv

Description

@dingqingy-nv

User problem

only 5%-ish speedup

Desired outcome

can we improve more?

Alternatives considered

No response

Affected area

area:perf

Urgency / use case

Important but not blocking

Extra context

No response

Metadata

Metadata

Assignees

No one assigned

    Labels

    26.04.01featureNew capabilities, enhancements, or enablement workneeds-triageNew item needs classification and ownershipperformance/releasePerformance items related with NeMo release

    Type

    Projects

    No projects

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions