Using CUDA while decoupling from the CUDA Toolkit as a hard-dependency #365
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
Using CUDA while decoupling from the CUDA Toolkit as a hard-dependency Possible solution for SciSharp#350 Adding an alternative, fallback method of detection system-supported cuda version to make CUDA Toolkit installation optional. Technically, it uses output of the command line tool "nvidia-smi" (preinstalled with nvidia drivers), which also contains information about cuda version supported on system. Can confirm it works only on Windows, but I suppose that similar approach can be utilized for Linux and MacOS as well. Didn't touch the code for these 2 platforms, nevertheless. After that, cuda can be utilized simply by putting nvidia libraries from llama.cpp original repo, "bin-win-cublas-cu12.2.0-x64.zip" asset to the root folder of the built program. For example, to folder: "\LLama.Examples\bin\Debug\net8.0\".
AsakusaRinne
approved these changes
Dec 14, 2023
There was a problem hiding this comment.
The overall looks good to me. Thank you for this contribution! Now it's much easier for us to support the case in #350
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Outdated suggestions cannot be applied.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.
Using CUDA while decoupling from the CUDA Toolkit as a hard-dependency
Possible solution for #350
Adding an alternative, fallback method of detection system-supported cuda version to make CUDA Toolkit installation optional. Technically, it uses output of the command line tool "nvidia-smi" (preinstalled with nvidia drivers), which also contains information about cuda version supported on system.
Can confirm it works only on Windows, but I suppose that similar approach can be utilized for Linux and MacOS as well. Didn't touch the code for these 2 platforms, nevertheless.
After that, cuda can be utilized simply by putting nvidia libraries from llama.cpp original repo, "bin-win-cublas-cu12.2.0-x64.zip" asset to the root folder of the built program. For example, to folder: "\LLama.Examples\bin\Debug\net8.0".