fix cblas_sgemm call in ggml_compute_forward_mul_mat_*? #838
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
|
The code comes from 2a2e63c by @ggerganov |
ggerganov
approved these changes
Apr 7, 2023
|
ah, makes sense, thank you! |
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Outdated suggestions cannot be applied.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.
Hey, I was trying to understand how blas was used in llama.cpp and maybe i found a bug?
at least i dont understand why - the int after the x in cblas_sgemm calls should be the pitch(or stride) of array x.
but x comes from src0 in all the ggml_compute_forward_mul_mat_*, so i am guessing the stride of src0 should be used, which is ne00?
sorry if i am missing something : (