This repository was archived by the owner on Aug 7, 2024. It is now read-only.

This repository was archived by the owner on Aug 7, 2024. It is now read-only.

add option to use fast accumulation in the float8 matmul #245

Closed

Closed

add option to use fast accumulation in the float8 matmul#245

torch._scaled_mm has a use_fast_accum flag to control the accumulation setting, we should expose it in float8_experimental

as requested by @lw

Metadata

Assignees

No one assigned

Labels

No labels

No labels

Type

No type

Projects

No projects

Milestone

No milestone

Relationships

None yet

Development

No branches or pull requests