[Serve.llm][P/D] Fix health check in prefill disagg #53937
Merged
Conversation
This file contains hidden or 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
kouroshHakha
commented
Jun 18, 2025
| @@ -466,25 +469,10 @@ async def __init__( | |||
|
|
|||
| self.response_postprocessor = ResponsePostprocessor() | |||
|
|
|||
| @property | |||
There was a problem hiding this comment.
This is useless. I don't know why we had it. removing.
kouroshHakha
commented
Jun 18, 2025
| @@ -816,9 +816,9 @@ async def check_health(self) -> None: | |||
| raise RuntimeError(f"{type(self.engine)} does not support health check.") | |||
|
|
|||
| try: | |||
| return await asyncio.wait_for(self.engine.check_health(), timeout=15) | |||
| await asyncio.wait_for(self.engine.check_health(), timeout=15) | |||
There was a problem hiding this comment.
removed the timeout time since ray serve has an adjustable timeout per deployment anyways.
kouroshHakha
commented
Jun 18, 2025
| @@ -160,13 +151,6 @@ async def _predict( | |||
| ): | |||
| yield chunk | |||
|
|
|||
| async def check_health(self) -> None: | |||
There was a problem hiding this comment.
These must be removed. In general the health check of a deployment is not bounded to the health check of its child deployments.
There was a problem hiding this comment.
cc @lk-chen fyi
kouroshHakha
commented
Jun 18, 2025
| @@ -232,12 +232,6 @@ async def _setup_handle_and_config_maps( | |||
|
|
|||
| async def check_health(self): | |||
| await self._init_completed.wait() | |||
| await asyncio.gather( | |||
There was a problem hiding this comment.
same thing applies here.
kouroshHakha
commented
Jun 19, 2025
| @@ -27,6 +27,7 @@ async def test_engine_metrics(): | |||
| model="Qwen/Qwen2.5-0.5B-Instruct", | |||
| dtype="auto", | |||
| disable_log_stats=False, | |||
| enforce_eager=True, | |||
There was a problem hiding this comment.
Making the tests faster
eicherseiji
approved these changes
Jun 19, 2025
kouroshHakha
commented
Jun 20, 2025
| @@ -170,8 +170,6 @@ async def test_check_health(self, llm_config: LLMConfig): | |||
|
|
|||
| await router.check_health() | |||
|
|
|||
| assert server.check_health.remote.call_count == 1 | |||
There was a problem hiding this comment.
testing router's health check has nothing to do with server's health check.
minerharry
pushed a commit
to minerharry/ray
that referenced
this pull request
Jun 27, 2025
Signed-off-by: Kourosh Hakhamaneshi <kourosh@anyscale.com>
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.
Also needs vllm-project/vllm#19821 to be merged.