Don't imply dynamic llama.cpp just because CUDA is on #671
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
MarcusDunn
approved these changes
Feb 24, 2025
|
did you intend to also modify the submodule? Looks good otherwise. |
|
No I did not. Need to revert. Hopefully can get to it today. |
Link against CUDA statically as well to maintain consistency with GGML_STATIC although technically that's our discretion.
vlovich
force-pushed
the
cuda-static-build
branch
from
a1c640b to
cfa76bd
Compare
|
Fixed. |
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Outdated suggestions cannot be applied.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.
Link against CUDA statically as well to maintain consistency with GGML_STATIC although technically that's our discretion. Verified that now just enabling CUDA still links llama.cpp statically (as well as all the supporting CUDA libraries which simplifies distribution).
Verified this works on Linux. Have not verified on Windows yet.