Skip to content

Fix autoquant do_bench import #162

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

Merged
merged 1 commit into from
Apr 23, 2024
Merged

Fix autoquant do_bench import #162

merged 1 commit into from
Apr 23, 2024

Conversation

msaroufim
Copy link
Member

@msaroufim msaroufim commented Apr 23, 2024

Just checking to see if CI passes

I might need to think a bit harder about nightly flags because in the case of reverts an IF_NIGHTLY flag will just break

Just checking to see if CI passes

I might need to think a bit harder about nightly flags
@facebook-github-bot facebook-github-bot added the CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed. label Apr 23, 2024
@msaroufim msaroufim requested review from cpuhrsch and HDCharles April 23, 2024 19:36
Copy link
Contributor

@HDCharles HDCharles left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

yeah this was what i was thinking we'd have to do

@msaroufim msaroufim merged commit bb06647 into main Apr 23, 2024
11 checks passed
dbyoung18 pushed a commit to dbyoung18/ao that referenced this pull request Jul 31, 2024
Just checking to see if CI passes

I might need to think a bit harder about nightly flags
yanbing-j pushed a commit to yanbing-j/ao that referenced this pull request Dec 9, 2024
* MPS quantization

* mps dtypes

* updates

* fix names

* typo

* no bfloat16 for older macOS

* fix typo

* remove failing embedding quantization from MPS runs

* bfloat -> current model precision

* typo

* missed bfloat16 to swotch to defaulkt precision

* remove int8 quantization on mps

* enable cpu fallback for mps on int4

* hack int4pack_mm for torch.float

* typo

* disable int4 because fp16 int4pack_mm not working for float16
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
CLA Signed This label is managed by the Facebook bot. Authors need to sign the CLA before a PR can be reviewed.
Projects
None yet
Development

Successfully merging this pull request may close these issues.

3 participants