Faster Q4_K on Metal #2290
Merged
Faster Q4_K on Metal #2290
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
ggerganov
approved these changes
Jul 20, 2023
|
I can provide results from M1 Pro a bit later |
|
M1 Pro
|
|
@ggerganov Any chance the 13B points are reversed? Else it would mean that on current master token prediction is about the same for 7B and 13B on your M1 Pro. |
|
Sorry about that, somehow I messed up the |
This was referenced Jul 20, 2023
Merged
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Outdated suggestions cannot be applied.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 improves token generation speed for
Q4_Kon Metal by a significant amount using ideas from PRs #2248, #2212 and #2188. The table gives token generation time in ms/t on M2 Max with 30-core GPU: