feat: Add extended sampling API with candidate token lists #14612 #14765
+222
−0
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
This commit implements the feature requested in issue ggml-org#14612, adding an extended sampling API that provides detailed information about the sampling process. Key changes: - Add llama_sampling_result struct to include/llama.h - Add llama_sampler_sample_with_candidates function - Add llama_sampling_result_free function for memory management - Update README.md with comprehensive API documentation The new API allows developers to: - Access selected token ID, logit, and probability - Get a list of candidate tokens with their probabilities - Debug sampling strategies and analyze model behavior - Build applications with insight into model decision-making Resolves: ggml-org#14612
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Outdated suggestions cannot be applied.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 commit implements the feature requested in issue #14612, adding an extended sampling API that provides detailed information about the sampling process.
Key changes:
The new API allows developers to:
Resolves: #14612
Make sure to read the contributing guidelines before submitting a PR