-
-
Notifications
You must be signed in to change notification settings - Fork 5.4k
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
[V1] Make AsyncLLMEngine v1-v0 opaque #11383
[V1] Make AsyncLLMEngine v1-v0 opaque #11383
Conversation
👋 Hi! Thank you for contributing to the vLLM project. Once the PR is approved and ready to go, your PR reviewer(s) can run CI to test the changes comprehensively before merging. To run CI, PR reviewers can do one of these:
🚀 |
Signed-off-by: Ricky Xu <[email protected]>
0ab6855
to
2604dbc
Compare
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. cc @WoosukKwon @robertgshaw2-neuralmagic
Test failures look unrelated on AMD. |
Signed-off-by: Ricky Xu <[email protected]>
Signed-off-by: Ricky Xu <[email protected]>
Signed-off-by: Ricky Xu <[email protected]>
Signed-off-by: Ricky Xu <[email protected]> Signed-off-by: Bowen Wang <[email protected]>
Signed-off-by: Ricky Xu <[email protected]>
Right now, users of the AsyncLLMEngine will have to modify their code to use V1 even if
VLLM_USE_V1=1
is used.We should have the V1/V0 behaviour changed by
VLLM_USE_V1
sorely as much as possible.