Add patch for WebGPU on Android to handle fp16 in uniforms #25349
Conversation
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
Contributor
|
Is there any existing f16 access to uniform buffer? |
Contributor
|
I think the patch should just work for all builds, including Linux, right? If it's already working with f16 in the old code, it should not be affected with the patched code. |
Contributor
Author
Sorry if I am misunderstanding the question, but the patch should only impact Android. I believe it should work on Linux theoretically, but wanted to minimize the impact so I limited to android |
fs-eire
reviewed
Jul 23, 2025
Member
fs-eire
added a commit
that referenced
this pull request
Jul 30, 2025
### Description For f16 uniform variables, use u32 to bit-wise represent them. ### Motivation and Context Some devices supports f16 in shader/storage buffer, but not in uniform buffers. Dawn will set the f16_support to false for them. However, we don't necessarily have to use f16 in uniform. This change together with #25349 will enable using f16 models on some Android devices.
fs-eire
approved these changes
Aug 4, 2025
adrianlizarraga
pushed a commit
that referenced
this pull request
Aug 8, 2025
### Description For f16 uniform variables, use u32 to bit-wise represent them. ### Motivation and Context Some devices supports f16 in shader/storage buffer, but not in uniform buffers. Dawn will set the f16_support to false for them. However, we don't necessarily have to use f16 in uniform. This change together with #25349 will enable using f16 models on some Android devices.
sanketkaleoss
pushed a commit
to sanketkaleoss/onnxruntime
that referenced
this pull request
Aug 11, 2025
### Description For f16 uniform variables, use u32 to bit-wise represent them. ### Motivation and Context Some devices supports f16 in shader/storage buffer, but not in uniform buffers. Dawn will set the f16_support to false for them. However, we don't necessarily have to use f16 in uniform. This change together with microsoft#25349 will enable using f16 models on some Android devices.
sanketkaleoss
pushed a commit
to sanketkaleoss/onnxruntime
that referenced
this pull request
Aug 11, 2025
…#25349) ### Motivation and Context Android devices (like S24) doesn't seem to allow fp16 in uniforms so the WebGPU EP has to manually handle passing an fp32 in the uniform and converting to fp16 before using.
gedoensmax
pushed a commit
to gedoensmax/onnxruntime
that referenced
this pull request
Sep 2, 2025
…#25349) ### Motivation and Context Android devices (like S24) doesn't seem to allow fp16 in uniforms so the WebGPU EP has to manually handle passing an fp32 in the uniform and converting to fp16 before using.
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.
Motivation and Context
Android devices (like S24) doesn't seem to allow fp16 in uniforms so the WebGPU EP has to manually handle passing an fp32 in the uniform and converting to fp16 before using.