llama: replace cuda feature with env var #266
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
This commit removes the `cuda` feature and replaces it with an environment variable `LLM_CHAIN_CUDA`.It also adds an additional environment variable `LLM_CHAIN_CUDA_LIB_PATH` which should be set to the path of the CUDA library directory, and include link libraries required for CUDA. Finally `-fPIC` is added to `CMAKE_CUDA_FLAGS`. The motivation for this is that having the feature `cuda` was not working as this will cause the build to fail if infact the CUDA library is not installed. I think that this may not have been the case with earlier versions of llama.cpp and perhaps why this was not an issue before. Signed-off-by: Daniel Bevenius <daniel.bevenius@gmail.com>
danbev
changed the title
williamhogman
approved these changes
Feb 2, 2024
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Outdated suggestions cannot be applied.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 commit removes the
cudafeature and replaces it with anenvironment variable
LLM_CHAIN_CUDA.It also adds an additionalenvironment variable
LLM_CHAIN_CUDA_LIB_PATHwhich should be set tothe path of the CUDA library directory, and include link libraries
required for CUDA. Finally
-fPICis added toCMAKE_CUDA_FLAGS.The motivation for this is that having the feature
cudawas notworking as this will cause the build to fail if infact the CUDA
library is not installed. I think that this may not have been the case
with earlier versions of llama.cpp and perhaps why this was not an
issue before.