July 2024 binaries #833
Merged
July 2024 binaries #833
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
…/runs/9743801974 for commit 1c5eba6f8e628fb0a98afb27d8aaeb3b0e136451
Add the libraries to runtime targets and nuget spec
… to commit to GitHub!
|
@martindevans I tested it on osx and it's working. I also changed the nuget packages to include sgml. |
|
Thanks! |
Fix possible file locks due to race conditions during build & test
|
The race condition in the build has been fixed, thanks to @m0nsky for the hard work! |
Manually load GGML dependency for Linux/OSX
|
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Outdated suggestions cannot be applied.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 updates LLamaSharp to a newer llama.cpp version (1c5eba6f8e628fb0a98afb27d8aaeb3b0e136451). Thanks to @m0nsky and @SignalRT for helping out with this!
This includes a couple of other related changes, due to upstream changes:
There is a major change in how binaries are distributed for development. Previously they were committed into this repo, in the runtimes/deps folder. However, the llama.cpp binaries have no grown over 100MB for CUDA, which exceeds the maximum GitHub file size.
To work around this binaries have been uploaded to a release in another repo (currently here, ownership will be transferred to SciSharp before this PR is closed). A new msbuild action has been added to LLamaSharp.csproj which automatically downloads and unzips the binaries.
Note that this version is now a week out of date, due to the hold up with the new build system. Once this has merged we may want to immediately do another binary update and then do a release. The important thing here is testing that this new approach works on all platforms!
To do:
ggml.dlls