Multiple context per model support #70
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
…w system has split model weights and contexts into two separate things, allowing one set of weights to be shared between many contexts. This change _only_ implements the low level API and makes no effort to update the LlamaSharp higher level abstraction. It is built upon llama `b3f138d`, necessary DLLs are **not** included in this commit.
- Additional comments
|
Thanks for doing this, I was planning to investigate something similar once my other PR was merged. LGTM 👍 In future PRs I'm hoping to push some of what's done in the |
Closed
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 participants
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Outdated suggestions cannot be applied.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 builds on top of PR #64 as that brought in the new native API changes needed to allow multiple contexts per model instance
Due to some unfortunate naming there are quite a few files changes, but I did that ins a seperate commit to make review a bit less painless
LLamaModel was renamed to LLamaModelContext and has very little changes, it now just takes a model as a parameter
Basic flow now
LLamaModel -> LLamaModelContext -> ILLammaExecutor
All examples should be updated and working, and the Web interface is activly using mutiple contexts, just open more tabs