cuda : fix disabling device with --tensor-split 1,0 #3951
Merged
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
cebtenzzre
force-pushed
the
fix-tensor-split-zero
branch
from
699ea6d to
05c51f9
Compare
slaren
approved these changes
Nov 5, 2023
ggerganov
reviewed
Nov 5, 2023
| @@ -7403,7 +7410,7 @@ static void ggml_cuda_mul_mat_mat_batched_cublas(const ggml_tensor * src0, const | |||
|
|
|||
| static void ggml_cuda_mul_mat(const ggml_tensor * src0, const ggml_tensor * src1, ggml_tensor * dst) { | |||
| const bool all_on_device = | |||
| (src0->backend == GGML_BACKEND_GPU) && | |||
| (src0->backend == GGML_BACKEND_GPU || src0->backend == GGML_BACKEND_GPU_SPLIT) && | |||
There was a problem hiding this comment.
The ggml_cuda_mul_mat_mat_batched_cublas branch does not currently support split tensors.
Would this break F16 models for multi-gpu?
olexiyb
pushed a commit
to Sanctum-AI/llama.cpp
that referenced
this pull request
Nov 23, 2023
Co-authored-by: slaren <[email protected]>
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Outdated suggestions cannot be applied.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 restores the functionality of PR #2506 after it was broken in PR #3110.
Before:
With both this PR and #3944 applied (otherwise multi-GPU doesn't work at all), both of the above commands work as expected.