CUDA: support for mat. mul. with ne03 != ne13 #11656
Merged
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
slaren
approved these changes
Feb 4, 2025
a33f0f5 to
9887021
Compare
|
I don't understand why the server CI jobs are failing, for some reason the server isn't online after 12 seconds. Can I assume it's unrelated to my changes? |
|
It's probably failing to download the test model from HF, happens occasionally. |
tinglou
pushed a commit
to tinglou/llama.cpp
that referenced
this pull request
Feb 13, 2025
orca-zhang
pushed a commit
to orca-zhang/llama.cpp
that referenced
this pull request
Feb 26, 2025
arthw
pushed a commit
to arthw/llama.cpp
that referenced
this pull request
Feb 26, 2025
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Outdated suggestions cannot be applied.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 adds CUDA support for matrix multiplications with
ne03 != ne13. I added support toggml_cuda_op_mul_matwhich provides the kernels with pointers on which they can perform matrix multiplications as if dimensions 2 and 3 had size 1. However, because this adds a lot of overhead I also extendedmul_mat_vecfor batched matrix vector multiplication support in dimension 3.