Skip to content

Conversation

@njhill
Copy link
Member

@njhill njhill commented Apr 25, 2024

Called when the LLMEngine is garbage collected. The executor might not otherwise be garbage collected itself if it is referenced from other threads.

Default is no-op but can be overwritten by subclasses.

In preparation for introducing a MultiprocessingGPUExecutor.

Called when the LLMEngine is garbage collected. The executor might not otherwise be garbage collected itself if it is referenced from other threads.

Default is no-op but can be overwritten by subclasses.

In preparation for introducing a `MultiprocessingGPUExecutor`.
@njhill njhill requested a review from zhuohan123 April 25, 2024 17:44
@njhill njhill merged commit 15e7c67 into vllm-project:main Apr 25, 2024
@njhill njhill deleted the executor_shutdown branch April 25, 2024 23:32
robertgshaw2-redhat pushed a commit to neuralmagic/nm-vllm that referenced this pull request May 6, 2024
z103cb pushed a commit to z103cb/opendatahub_vllm that referenced this pull request May 7, 2024
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.

3 participants