Batch Queueing #761
Merged
Batch Queueing #761
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
…t of work to be queued up in the executor and run in batches. This is helpful when prompting with very large numbers of tokens (e.g. a 2000 character system prompt would automatically be queued up in 4x512 batches). This is a pre-requisite for embeddings prompting (i.e. llava), which needs an entirely new type of item in the batch queue.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
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Outdated suggestions cannot be applied.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.
Added a batch queue to
BatchedExecutor, allowing an arbitrary amount of work to be queued up in the executor and run in batches. This is helpful when prompting with very large numbers of tokens (e.g. a 2000 character system prompt would automatically be queued up in 4x512 batches).This is a pre-requisite for embeddings prompting (i.e. llava), which needs an entirely new type of item in the batch queue. Embeddings usually also come in large numbers (e.g. one llava image might be hundreds of items), so the ability to queue up lots of work is valuable!