vulkan: Use push constant offset to handle misaligned descriptors #10987
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
github-actions
bot
added
Vulkan
0cc4m
approved these changes
Dec 29, 2024
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Outdated suggestions cannot be applied.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.
For #10984.
Compute descriptor misalignment for unary/binary ops, and put the offset in a push descriptor which the shader adds to the index. I did this for all the unary/binary ops except get_rows_quant because those use the quant type for the buffer block and so the indexing wouldn't work.
I don't think test_backend_ops has good coverage for non-zero offsets, so please help suggest and tests I should run. I ran llama-cli on a couple models.