Open BenjaminBossan opened 2 weeks ago
The docs for this PR live here. All of your documentation changes will be reflected on that endpoint. The docs are available until 30 days after the last update.
With https://github.com/huggingface/transformers/pull/33361 being merged (which marks torchao as traininable), once the next transformers version is released (>4.44.2), the GPU tests on this PR should pass (I tested locally). This PR should not be merged before that.
Check out this pull request on
See visual diffs & provide feedback on Jupyter Notebooks.
Powered by ReviewNB
Add support for torchao.
The current status is:
int8_weight_only
works fullyint8_dynamic_activation_int8_weight
only works partly (asdequantize
is not supported, merging and DoRA won't work)int4_weight_only
not supported as some ops for forward call are missingnf4
not supported on transformers side