Skip to content

[Feature Request] FP8 block quant support for AR+RMSNOrm , AR+RMSNorm+Quant. #2073

@kmrao-nv

Description

@kmrao-nv

More details here:
vllm-project/vllm#28423

Metadata

Metadata

Assignees

No one assigned

    Labels

    Type

    No type

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions