Prompt caching in mlx_lm.server
#1026
Merged
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
|
This would not be back wards compatible with any later incorporation of batched input for generate (i.e., #948) |
chimezie
suggested changes
Oct 12, 2024
| @@ -474,15 +531,15 @@ def handle_completion( | |||
|
|
|||
| def handle_stream( | |||
| self, | |||
| prompt: mx.array, | |||
| prompt: List[int], | |||
There was a problem hiding this comment.
This in particular. Can't we handle a single or multiple (batched) prompt that falls back to the behavior for a single prompt by default?
There was a problem hiding this comment.
We can always update this type to List[List[int]] when the time comes.
angeloskath
approved these changes
Oct 14, 2024
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Outdated suggestions cannot be applied.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.
Added a basic prompt cache in
mlx_lm.serverfor chat mode. But it does support chatting with cache reuse.