Skip to content

Update ipex backend to be deprecated.#1599

Merged
XuehaoSun merged 7 commits intomainfrom
xinhe/3-23c
Mar 24, 2026
Merged

Update ipex backend to be deprecated.#1599
XuehaoSun merged 7 commits intomainfrom
xinhe/3-23c

Conversation

@xin3he
Copy link
Copy Markdown
Contributor

@xin3he xin3he commented Mar 23, 2026

Description

Update ipex backend to be deprecated.

Type of Change

  • Bug fix
  • New feature
  • Documentation update
  • Performance improvement
  • Code refactoring
  • Other (please specify):

Related Issues

Fixes or relates to #1427

Checklist Before Submitting

  • My code has been tested locally.
  • Documentation has been updated as needed.
  • New or updated tests are included where applicable.

Copilot AI review requested due to automatic review settings March 23, 2026 12:27
Signed-off-by: Xin He <xin3.he@intel.com>
Copy link
Copy Markdown
Contributor

Copilot AI left a comment

Choose a reason for hiding this comment

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

Pull request overview

Deprecates the IPEX inference backend by shifting user guidance toward the ark (auto-round-lib) backend and emitting a runtime deprecation warning when IPEX is used, aligning with the discussion in #1427.

Changes:

  • Update English/Chinese step-by-step docs to recommend ark for CPU/Intel GPU inference and mark IPEX as “to be deprecated”.
  • Add a one-time deprecation warning when an ipex* backend is detected during inference post-init.
  • Expand ark backend metadata to include bfloat16 in supported compute dtypes.

Reviewed changes

Copilot reviewed 4 out of 4 changed files in this pull request and generated 6 comments.

File Description
docs/step_by_step.md Updates inference backend recommendations and backend support table (EN).
docs/step_by_step_CN.md Same doc updates for the Chinese translation (CN).
auto_round/inference/convert_model.py Emits a one-time deprecation warning when IPEX backends are used.
auto_round/inference/backend.py Updates ark backend metadata to include BF16 in compute_dtype.

xin3he and others added 6 commits March 24, 2026 09:33
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
Co-authored-by: Copilot <175728472+Copilot@users.noreply.github.com>
@xin3he
Copy link
Copy Markdown
Contributor Author

xin3he commented Mar 24, 2026

/azp run Unit-Test-CUDA-AutoRound

@azure-pipelines
Copy link
Copy Markdown

Azure Pipelines successfully started running 1 pipeline(s).

@XuehaoSun XuehaoSun merged commit 88824a1 into main Mar 24, 2026
37 of 40 checks passed
@XuehaoSun XuehaoSun deleted the xinhe/3-23c branch March 24, 2026 03:53
@chensuyue chensuyue added this to the 0.12.0 milestone Mar 27, 2026
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.

6 participants