Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

feat: move allocation logic to rust #1835

Merged
merged 3 commits into from
Jun 5, 2024

Conversation

OlivierDehaene
Copy link
Member

@OlivierDehaene OlivierDehaene commented Apr 30, 2024

Close #2007

Copy link
Collaborator

@Narsil Narsil left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

NIce

Cargo.toml Show resolved Hide resolved
window_size: Option<u32>,
) -> Self {
// Create channel
let (sender, receiver) = mpsc::unbounded_channel();
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Unrelated to the PR, but maybe it's a culprit for the leaks.

https://docs.rs/tokio/latest/tokio/sync/mpsc/fn.unbounded_channel.html

router/src/queue.rs Outdated Show resolved Hide resolved
router/src/queue.rs Outdated Show resolved Hide resolved
server/Makefile-flash-att-v2 Outdated Show resolved Hide resolved
server/text_generation_server/models/flash_causal_lm.py Outdated Show resolved Hide resolved
router/src/block_allocator.rs Outdated Show resolved Hide resolved
router/src/block_allocator.rs Outdated Show resolved Hide resolved
router/src/block_allocator.rs Outdated Show resolved Hide resolved
@github-actions github-actions bot removed the Stale label Jun 1, 2024
Narsil
Narsil previously approved these changes Jun 4, 2024
Copy link
Collaborator

@Narsil Narsil left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

router/src/infer/v3/queue.rs Outdated Show resolved Hide resolved
router/src/infer/v3/queue.rs Outdated Show resolved Hide resolved
@OlivierDehaene OlivierDehaene merged commit 8aece3b into main Jun 5, 2024
7 checks passed
@OlivierDehaene OlivierDehaene deleted the feat/move_cache_manager_rust branch June 5, 2024 10:18
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

CacheManager.allocate is slow in the prefill when using large num_blocks
3 participants