Disable SDP on BF16 default for generic diffusers HPU support#2251
Merged
regisss merged 1 commit intohuggingface:mainfrom Sep 10, 2025
Merged
Disable SDP on BF16 default for generic diffusers HPU support#2251regisss merged 1 commit intohuggingface:mainfrom
regisss merged 1 commit intohuggingface:mainfrom
Conversation
Signed-off-by: Daniel Socek <daniel.socek@intel.com>
|
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. |
astachowiczhabana
pushed a commit
that referenced
this pull request
Sep 11, 2025
Signed-off-by: Daniel Socek <daniel.socek@intel.com>
astachowiczhabana
pushed a commit
that referenced
this pull request
Sep 17, 2025
Signed-off-by: Daniel Socek <daniel.socek@intel.com>
gplutop7
pushed a commit
to HabanaAI/optimum-habana-fork
that referenced
this pull request
Oct 15, 2025
…gface#2251) (huggingface#671) Signed-off-by: Daniel Socek <daniel.socek@intel.com> Co-authored-by: Daniel Socek <daniel.socek@intel.com>
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
What does this PR do?
HPU OOB functionality for diffusers' models use GPU-HPU Migration Toolkit. After 1.21 we default to eager mode where the default SDP kernel is in FP32 precision. Previously, the default lazy mode in GPU-HPU Migration Toolkit used SDP in BF16 precision (SW-226104). This causes performance degradation. huggingface/diffusers#12310 PR is submitted to improve performance on HPU devices.
In OH we want to keep the default as is, which is what this PR is for.