demo_page_hf: use float16 on CUDA and float32 on CPU to fix 'slow_conv2d_cpu' Half error - #122
Merged
Conversation
…v2d_cpu' Half error
Alberto02003
pushed a commit
to Alberto02003/Dolphin
that referenced
this pull request
Sep 27, 2025
Fixes 'slow_conv2d_cpu' Half error when running demo_page_hf.py on CPU. - Use float16 precision only on CUDA devices for performance - Use float32 precision on CPU for compatibility - Maintains backward compatibility with existing CUDA workflows Resolves bytedance#122
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
2 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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
Running
demo_page_hf.pyon CPU fails with: “slow_conv2d_cpu not implemented for 'Half'”.Root cause
Both the model and
pixel_valueswere always forced to float16, even when running on CPU.Fix
half()only when CUDA is available; usefloat()on CPU.pixel_values.half()only on CUDA; usepixel_values.float()on CPU.Impact
Scope
demo_page_hf.pyonly.