Recompute when the deadlock is detected #278
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
mrwyattii
approved these changes
Nov 9, 2023
| @@ -147,6 +147,10 @@ class RaggedRequest: | |||
| _generated_tokens: List[torch.Tensor] = field(default_factory=list) | |||
| _finish_reason: GenerationFinishReason = GenerationFinishReason.NONE | |||
|
|
|||
| @property | |||
| def prompt_length(self) -> int: | |||
There was a problem hiding this comment.
In the case we have deadlock, the prompt_length will be incorrect on the output. Perhaps we need to store original_prompt_length or something like that. Don't worry about this for now. I have plans to expand the output details and can handle this in a future PR.
There was a problem hiding this comment.
I see, you are right. I would appreciate it if you could fix it on your PR
mrwyattii
approved these changes
Nov 10, 2023
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Outdated suggestions cannot be applied.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.
Wit this PR, the scheduler clears the KV cache and recomputes it when the deadlock is detected.