-
Notifications
You must be signed in to change notification settings - Fork 254
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
Update Metal, CUDA Candle impls and ISQ #816
base: master
Are you sure you want to change the base?
Conversation
Code Metrics Report=============================================================================== Language Files Lines Code Comments Blanks =============================================================================== C Header 2 35 28 0 7 Dockerfile 1 34 25 0 9 Happy 1 442 369 0 73 JSON 12 105 104 0 1 Python 52 2268 1930 69 269 TOML 20 625 559 2 64 YAML 2 21 19 2 0 ------------------------------------------------------------------------------- Jupyter Notebooks 4 0 0 0 0 |- Markdown 2 77 32 31 14 |- Python 2 196 169 1 26 (Total) 273 201 32 40 ------------------------------------------------------------------------------- Markdown 38 2760 0 2094 666 |- BASH 6 103 100 0 3 |- JSON 1 12 12 0 0 |- Python 5 92 82 0 10 |- Rust 9 322 274 0 48 |- TOML 2 75 63 0 12 (Total) 3364 531 2094 739 ------------------------------------------------------------------------------- Rust 260 75643 68177 1547 5919 |- Markdown 123 1217 25 1117 75 (Total) 76860 68202 2664 5994 =============================================================================== Total 393 81933 71211 3714 7008 =============================================================================== |
|
Hi @ChristianWeyer thanks for testing it! I pushed some changes which should hopefully fix this, can you please test it again? I made some changes to things which will affect the UQFF backend - could you also please quickly test that:
And then:
Sorry for the inconvenience! My Metal hardware should be arriving soon :) |
Here we go:
|
@ChristianWeyer thanks, I added a quick cast - could you please try it again? |
|
@ChristianWeyer I think this should compile now, can you please test it :)? Also, please, the UQFF:
And then:
Thanks! |
|
Metal: MLX
CUDA: PaddedData for quantized
@ChristianWeyer could you please test if this builds on Metal?