fix: add Float8 dtype fallback in modeling_utils.py#44616
Closed
s-zx wants to merge 1 commit intohuggingface:mainfrom
Closed
fix: add Float8 dtype fallback in modeling_utils.py#44616s-zx wants to merge 1 commit intohuggingface:mainfrom
s-zx wants to merge 1 commit intohuggingface:mainfrom
Conversation
Float8_e4m3fn dtypes may not be available in all PyTorch builds. Add fallback to bfloat16 when Float8 dtype fails to prevent TypeError during model loading. Fixes huggingface#44589 Signed-off-by: s-zx <2575376715@qq.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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Add fallback to bfloat16 when Float8 dtype fails to set, preventing TypeError when loading FP8 models on PyTorch builds without Float8_e4m3fnStorage support.
Root Cause
torch.set_default_dtype(dtype)raisesTypeError: couldn't find storage object Float8_e4m3fnStoragewhen Float8 is not available.Fix
Wrap in try/except and fall back to bfloat16 when the error indicates Float8.
Fixes #44589