-
Notifications
You must be signed in to change notification settings - Fork 1.1k
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
[TENSORRT-LLM] - Implement new looper thread based backend #2357
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
# Conflicts: # backends/trtllm/src/backend.rs
…<T, tensorrt_llm::common::TllmException>
…e pulling in a single step
mfuntowicz
force-pushed
the
trtllm-executor-thread
branch
from
October 21, 2024 10:31
7f02f49
to
fb00f98
Compare
This reverts commit 3174716
Narsil
previously approved these changes
Oct 25, 2024
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
LGTM.
Narsil
approved these changes
Oct 25, 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Outdated suggestions cannot be applied.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.
Current backend implementation relies on locking mecanism to access, within each tokio's requests context thread, the executor on the C++ side.
This locking results in a heavy contention for all clients except the one which already acquired the lock in write mode.
This is inherent to the tokio's RwLock implementation which is giving priority to writers.
This backend implement a new, background thread based, TensorRT-LLM backend.
Everything related to the executor happens within this sole background thread and thus doesn't need any
Sync
norRwLock
to be implemented to make it work.The only required trait is
Send
to be able to move the backend from the creator thread to the background thread in order to catch backend creation issue.