Skip to content

Add maca backend. #25

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 7 commits into from
Closed

Conversation

Reinerzhou
Copy link
Member

Motivation

Add maca backend.

Modification

Add maca device and op_backend.

Checklist

  1. Pre-commit or other linting tools are used to fix the potential lint issues.
  2. The modification is covered by complete unit tests. If not, please add more unit tests to ensure the correctness.
  3. If the modification has a dependency on downstream projects of a newer version, this PR should be tested with all supported versions of downstream projects.
  4. The documentation has been modified accordingly, like docstring or example tutorials.

AllentDan and others added 3 commits October 22, 2024 18:38
* refine pre-post-process

* pytorch engine uses modelagent stream

* put num_appendable_ids.cuda() back
* feat(ascend): support w4a16

* refactor ascend awq_linear

* update doc

* refine code

* update code

* rebase main
@Reinerzhou Reinerzhou force-pushed the zhousl/maca_dev branch 2 times, most recently from 4a67d6b to 2581dbe Compare October 23, 2024 05:39
@Reinerzhou Reinerzhou closed this Nov 18, 2024
@Reinerzhou Reinerzhou deleted the zhousl/maca_dev branch November 18, 2024 10:28
@Reinerzhou Reinerzhou restored the zhousl/maca_dev branch November 18, 2024 10:28
@Reinerzhou Reinerzhou deleted the zhousl/maca_dev branch November 18, 2024 10:28
@Reinerzhou Reinerzhou restored the zhousl/maca_dev branch November 18, 2024 10:28
@Reinerzhou Reinerzhou deleted the zhousl/maca_dev branch February 20, 2025 08:24
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.

4 participants