[experimental] ggml C++ bindings #581
Draft
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
Green-Sky
reviewed
Oct 15, 2023
|
I think using |
ggerganov
reviewed
Oct 15, 2023
There was a problem hiding this comment.
The graph building code looks very clean.
The context stack should probably be thread_local so that we can build graphs in parallel threads.
I am also not sure if we need the C++ bindings. Some things indeed get much easier to implement in C++. Maybe if we limit the bindings scope to some very basic things like auto deallocation of resources and scoped-contexts it wouldn't be a problem to maintain them.
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Outdated suggestions cannot be applied.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.
Adds an example with C++ bindings, and the gpt-2 example adapted to use these bindings.
At this point this is mostly an experiment to see how ggml C++ bindings could look like. I am not sure if this is something that we may want at all.
The advantage over the C API would be automatic resource freeing, and maybe a nicer syntax in some cases.