[Serve.llm][P/D] Support separate deployment config for PDProxy in Prefill disagg #53821
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
This comment was marked as outdated.
This comment was marked as outdated.
Sorry, something went wrong.
There was a problem hiding this comment.
Pull Request Overview
This PR introduces a dedicated deployment configuration for the PDProxy component in the prefill-decode disaggregated flow, allowing users to pass custom Ray Serve options.
- Added a new
proxy_deployment_configfield toPDServingArgsfor arbitrary Ray Serve deployment parameters. - Forwarded
proxy_deployment_configthroughparse_args. - Applied the custom options in
build_appvia.options(**pd_config.proxy_deployment_config)on thePDProxyServerdeployment.
Comments suppressed due to low confidence (2)
python/ray/llm/_internal/serve/deployments/prefill_decode_disagg/prefill_decode_disagg.py:42
- [nitpick] Consider expanding this description to list common keys (e.g.,
num_replicas,ray_actor_options) or link directly to the Ray Serve deployment options docs for easier discoverability.
The Ray @server.deployment options for the proxy server.
python/ray/llm/_internal/serve/deployments/prefill_decode_disagg/prefill_decode_disagg.py:205
- Add unit or integration tests to verify that various
proxy_deployment_configparameters (e.g., replicas, resource tags) are correctly applied and take effect on thePDProxyServerdeployment.
.options(**pd_config.proxy_deployment_config)
eicherseiji
approved these changes
Jun 16, 2025
elliot-barn
pushed a commit
that referenced
this pull request
Jun 18, 2025
…efill disagg (#53821) Signed-off-by: kouroshhakha <kourosh@anyscale.com> Signed-off-by: elliot-barn <elliot.barnwell@anyscale.com>
rebel-scottlee
pushed a commit
to rebellions-sw/ray
that referenced
this pull request
Jun 21, 2025
…efill disagg (ray-project#53821) Signed-off-by: kouroshhakha <kourosh@anyscale.com> Signed-off-by: Scott Lee <scott.lee@rebellions.ai>
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.
This PR is simple. It adds a separate configuration for controlling deployment config of PDProxy