ggml-cpu: Add get_rows support for Q6_K REPACK#20396
Draft
Alcpz wants to merge 1 commit intoggml-org:masterfrom
Draft
ggml-cpu: Add get_rows support for Q6_K REPACK#20396Alcpz wants to merge 1 commit intoggml-org:masterfrom
Alcpz wants to merge 1 commit intoggml-org:masterfrom
Conversation
github-actions
bot
added
the
ggml
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Tests with CPU_REPACK + models with tied embeddings result duplicated tensors, as CPU_REPACK currently doesn't support GET_ROWS.
This has high impact when trying to run small models on low memory devices like phones, E.g:
The PR addresses this by adding generic support (only for Q6_K, as that's the standard for the output layer).
Creating as draft as #16743 provides the same work (and this PR is based on that PR essentially). Will try to see if the other PR can be merged in, if not, I'll add proper validation (perplexity, llama-bench).