backend: build with CUDA compute 5.0 support by default #3499
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
Signed-off-by: Jared Van Bortel <[email protected]>
Signed-off-by: Jared Van Bortel <[email protected]>
|
CUDA is still working on Linux with this change. The installer size only seems to be around 1MiB bigger. I don't have a compute 5.0 GPU to test on however. |
manyoso
approved these changes
Feb 18, 2025
Signed-off-by: Jared Van Bortel <[email protected]>
|
A user with a GTX 950M confirmed in the linked issue that this patch works. |
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Outdated suggestions cannot be applied.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.
It is possible that our llama.cpp backend is compatible with CUDA compute 5.0 GPUs such as the GTX 750 from 2014. This was not believed to be the case before since upstream llama.cpp has not mentioned this officially that I know of, but apparently ollama includes compute 5.0 support in its CUDA 11 backend. We are also using CUDA 11, so it is worth a shot.
Fixes #3481