Draft
Conversation
Recent conversations (especially in the [machine learning working group]) suggest a need for a more specialized version of wasi-nn targeting LLMs. This change proposes such an interface, allowing users to access an ML `graph` directly using prompt strings instead of through the original tensor-based interface (i.e., `inference`). [machine learning working group]: https://github.com/bytecodealliance/meetings/tree/main/machine-learning/
Contributor
|
Are you assuming that all LLMs have intrinsic tokenization? Not all foundation models are transforms from string to string. Is the implication is that kv-cache and other stateful items will be kept opaquely by this context rather than maintained by the caller? |
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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Recent conversations (especially in the machine learning working group) suggest a need for a more specialized version of wasi-nn targeting LLMs. This change proposes such an interface, allowing users to access an ML
graphdirectly using prompt strings instead of through the original tensor-based interface (i.e.,inference).