Closed faaany closed 4 months ago
@echarlaix pls have a review. Thx!
@yao-matrix
Hi @IlyasMoutawwakil could you help review this PR? Thanks a lot!
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.
To fix the code style test you can do the following :
pip install .[quality]
make style
Hi @echarlaix, there are some CI tests failing. Do you know what I can do to fix them? Thx!
What does this PR do?
This PR adds XPU support for loading a Torchscript model using
IPEXModel.from_pretrained
. Below is a test example:Please note that
faaany/bert-base-uncased-float32-traced
is just a test model, which is traced from "google-bert/bert-base-uncased". Since I didn't load any tokenizer config, so I passmodel_id_tokenizer
toAutoTokenizer
in the example above.