-
Notifications
You must be signed in to change notification settings - Fork 359
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Updated Binaries December 2023 #361
Updated Binaries December 2023 #361
Conversation
LLama/Native/LLamaKvCacheView.cs
Outdated
/// </summary> | ||
/// <param name="view"></param> | ||
[DllImport(libraryName, CallingConvention = CallingConvention.Cdecl)] | ||
public static extern unsafe void llama_kv_cache_view_free(LLamaKvCacheView* view); |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
This is an amazing feature!
- Renamed `LLamaModelKvOverride` to `LLamaModelMetadataOverride`
bc095e6
to
b868b05
Compare
…broken (converter is never called)
Ok this is ready for review now. The CI has run tests for Windows, Linux and Mac (x64). Just MacOS ARM left! |
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Great work!
Some discussion about this in #350, which might end up being merged into this PR. If you'd rather not wait, we can merge this PR and put out a release right away. The cudart stuff can be added in a patch update at any time. |
If it's convenient for you, then feel free to do so. :) |
It's checked on OSX-ARM. It's Ok for me. |
Thanks for testing that @SignalRT. I think I'll merge this one now, cudart stuff can come in a later PR. |
This build includes AVX and AVX2 for MacOS x86_64. If anyone has an Intel Mac testing would be much appreciated!
Todo:
MetadataOverride
Testing: