Skip to content
This repository has been archived by the owner on Aug 7, 2024. It is now read-only.

[wip] add axiswise granularity to Float8Tensor #351

Closed
wants to merge 4 commits into from
Closed

[wip] add axiswise granularity to Float8Tensor #351

wants to merge 4 commits into from

Commits on Jul 26, 2024

  1. [wip] add axiswise granularity to Float8Tensor 

    Summary:

This PR adds the axiswise scaling granularity to `Float8Tensor` and
ensures that basic ops like transpose and `torch._scaled_mm` work as
expected.

A future PR will add integration with `Float8Linear`.

Test Plan:

TODO

Reviewers:

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
    @vkuzo
    vkuzo committed Jul 26, 2024
    Configuration menu
    Copy the full SHA
    e87f005 View commit details
    Browse the repository at this point in the history

  2. Update on "[wip] add axiswise granularity to Float8Tensor" 

    Summary:

This PR adds the axiswise scaling granularity to `Float8Tensor` and
ensures that basic ops like transpose and `torch._scaled_mm` work as
expected.

A future PR will add integration with `Float8Linear`.

Test Plan:

TODO

Reviewers:

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
    @vkuzo
    vkuzo committed Jul 26, 2024
    Configuration menu
    Copy the full SHA
    c4c9ae8 View commit details
    Browse the repository at this point in the history

Commits on Jul 28, 2024

  1. Update on "[wip] add axiswise granularity to Float8Tensor" 

    Summary:

This PR adds the axiswise scaling granularity to `Float8Tensor` and
ensures that basic ops like transpose and `torch._scaled_mm` work as
expected.

A future PR will add integration with `Float8Linear`.

Test Plan:

TODO

Reviewers:

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
    @vkuzo
    vkuzo committed Jul 28, 2024
    Configuration menu
    Copy the full SHA
    1052066 View commit details
    Browse the repository at this point in the history

  2. Update on "[wip] add axiswise granularity to Float8Tensor" 

    Summary:

This PR adds the axiswise scaling granularity to `Float8Tensor` and
ensures that basic ops like transpose and `torch._scaled_mm` work as
expected.

A future PR will add integration with `Float8Linear`.

Test Plan:

TODO

Reviewers:

Subscribers:

Tasks:

Tags:

[ghstack-poisoned]
    @vkuzo
    vkuzo committed Jul 28, 2024
    Configuration menu
    Copy the full SHA
    29fdaac View commit details
    Browse the repository at this point in the history