use '-e webgpu' to generate a model for webgpu #1278
Merged
Conversation
This file contains 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
Should we wait for microsoft/onnxruntime#22987 before merging this PR? |
Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>
Co-authored-by: kunal-vaishnavi <115581922+kunal-vaishnavi@users.noreply.github.com>
|
Should be ok without that PR. microsoft/onnxruntime#22987 fixes the issue with packed qkv and ROE inside GQA. |
kunal-vaishnavi
approved these changes
Feb 26, 2025
|
@guschmue Makes sense! 🚀 |
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Outdated suggestions cannot be applied.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.
change webgpu from '-e web' to '-e webgpu' for consistency.
We now use GQA instead of MHA and added a extra_option "use_webgpu_fp32=1" to enabled gpu's that do not support fp16.