ggml webgpu: actually add softmax, fix rms_norm offset #16400
Merged
+10
−1
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
github-actions
bot
added
the
ggml
CISC
approved these changes
Oct 3, 2025
|
Mind you, there appears to be an issue with |
|
fixed the soft max shader and added a temporary fix that blocks on each WebGPU queue submission until I figure out a more efficient way to wait for futures to complete. |
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Outdated suggestions cannot be applied.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.
In my previous PR (#16357), I missed cherry-picking a commit and ended up missing the code to actually enable soft_max (oops). This PR actually adds it to
supports_opandencode_node, as well as fixes a potential bug inrms_normwhere it was using the wrong offset into the tensor.