-
Notifications
You must be signed in to change notification settings - Fork 4.2k
Add base framework for flat bindings #3068
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
Closed
Closed
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
My recent addtions were illuminating. If you load vulkan and cuda then your chosen device ends up being whichever was loaded first (using ggml_backend_load_best) At least that's what happens when my 4070 is both cuda and vulkan device Oddly vulkan was faster - that may be down to NVIDIA's current diver problems though Done with this PR - can it be reviewed now? |
Arggh - Mac needs a few fixups |
Mac now happy |
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Outdated suggestions cannot be applied.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 PR adds a new option to cmake - the BINDINGS_FLAT option
If undefined everything is the same as if it didn't exist making it completely benign
If defined it includes ggml-flat.cpp and whisper-flat.cpp to the build of the dynamic libraries whisper and ggml. These are intended to allow extra functionality to be exposed in the shared libs. This is intended to allow other languages to add stuff they need to the dynamic libraries.
There's only one function added to the libraries ATM - whisper_flat_backends_load_all() which just calls ggml_backends_load_all()
There are no functions in the GGML version at all (not worked out what's needed yet), this is, however, likely to have some entries eventually.