Enable eager prefill and prefix caching by default #732
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
arnavgarg1
approved these changes
Jan 8, 2025
|
Can we update the default values in our docs as well to reflect this change? |
tgaddair
reviewed
Jan 9, 2025
launcher/src/main.rs
Outdated
| @@ -508,7 +508,7 @@ struct Args { | |||
| /// Whether to use the prefix caching mechanism. This will skip computing attention on previously cached prefixes | |||
| /// in the prompt. Useful in cases where many queries need to be run over a shared context, or for long multi-turn | |||
| /// chats conversations. | |||
| #[clap(long, env)] | |||
| #[clap(default_value = "true", long, env)] | |||
There was a problem hiding this comment.
Are we confident this is stable enough to enable by default? I believe there are some open questions on this at the moment. Maybe we can start with just landing the eager prefill change.
|
@arnavgarg1 Not sure if this is the only thing that you meant, but I've added a line documentation to |
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Outdated suggestions cannot be applied.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.
No description provided.