Skip to content
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

Patch #1200

Open
wants to merge 9 commits into
base: main
Choose a base branch
from
Open

Patch #1200

wants to merge 9 commits into from

Conversation

jiqing-feng
Copy link
Collaborator

@jiqing-feng jiqing-feng commented Mar 17, 2025

Hi @echarlaix @IlyasMoutawwakil @sywangyi .

This is our 1st step to enable patched model + torch.compile. We plan to disable all ipex fuse linear patch because torch.compile also has fuse opimization. We cannot defaultly use torch.compile for patched models because there are still incompatible issues for flash attention.

We plan to enable the patched model + torch.compile in ipex 2.7 or 2.8

This PR works for non-generation models like bert as patched bert model has no flash attention which will block the torch.compile .

Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
Signed-off-by: jiqing-feng <jiqing.feng@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.

Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
@jiqing-feng jiqing-feng marked this pull request as ready for review March 18, 2025 04:36
Signed-off-by: jiqing-feng <jiqing.feng@intel.com>
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.

2 participants