这是indexloc提供的服务,不要输入任何密码
Skip to content

Conversation

@yao-matrix
Copy link
Contributor

  1. extend docs to cover more accelerators like intel XPU
  2. fix some places in examples where xpu enabling missed

@BenjaminBossan , pls help review, thx very much

fix some places in examples where xpu enabling missed

Signed-off-by: Yao, Matrix <matrix.yao@intel.com>
@HuggingFaceDocBuilderDev

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.

Copy link
Member

@BenjaminBossan BenjaminBossan left a comment

Choose a reason for hiding this comment

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

Thanks for helping to make the docs more device agnostic and for adjusting some more examples to work with XPU.

@BenjaminBossan BenjaminBossan merged commit e98a59e into huggingface:main Aug 8, 2025
2 of 14 checks passed
@yao-matrix yao-matrix deleted the doc-xpu branch August 8, 2025 14:06
cyyever pushed a commit to cyyever/peft that referenced this pull request Sep 4, 2025
…ce#2728)

* Set max_model_len when initializing vLLM instance

* Introduce vllm_max_model_len arg

* Replace vllm args with vllm_init_kwargs

* Update docstring

* Add missing import

* Remove default values from newly deprecated args

* Docs update

* Reverted to adding single arg for max_model_len

* Remove spurious import

* Remove spurious line

* style

---------

Co-authored-by: Quentin Gallouédec <quentin.gallouedec@huggingface.co>
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.

3 participants