opencl: add q8_0 mm support #16469
Draft
opencl: add q8_0 mm support #16469
+271
−19
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
ggml
|
This kernel looks familiar. 😄 |
Sure, it follows the same (but simplified) tiling approach as in your Vulkan kernel and tweaks for Adreno. Although not achieving the best performance, it's quite elegant (requires minimum preprocessing of weights) and quick to add support for new data formats. Will explore for further improvements. |
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Outdated suggestions cannot be applied.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.
This PR add q8_0 matrix matrix multiply support. This improves q8_0 prompt processing.
With Adreno 830,
master
build: 86df2c9 (6690)
This PR
build: 28d3073 (6706)