Implementation of simple load balance routing proxy server (#1953) #2124
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
…ect#1953) This PR introduce a new proxy server implementation for disaggregated pd, which support simple token&kv_cache aware load balance routing strategy for the disaggregated pd system compared with origin toy_proxy with round robin. No tested on real workload --------- Signed-off-by: ganyi <pleaplusone.gy@gmail.com>
|
👋 Hi! Thank you for contributing to the vLLM Ascend project. The following points will speed up your PR merge:
If CI fails, you can run linting and testing checks locally according Contributing and Testing. |
Collaborator
|
does this example rely on DP patch? |
Collaborator
Author
No, this is an totally independant proxy . |
Collaborator
|
OK, make sense for me. |
wangxiyuan
approved these changes
Jul 31, 2025
wangxiyuan
reviewed
Jul 31, 2025
| # Adapted from https://github.com/vllm-project/vllm/tests/v1/kv_connector/nixl_integration/toy_proxy_server.py | ||
|
|
||
| # SPDX-License-Identifier: Apache-2.0 | ||
|
|
Collaborator
There was a problem hiding this comment.
it's good to add some usage guide here to let users know how to run this exmaple in quick
Collaborator
Author
There was a problem hiding this comment.
Good advise, I'll add some example in the comments
Collaborator
|
Do we need both proxy server implementations in the example folder? We could keep either toy_proxy_server or the one from this PR? |
Collaborator
Author
Sounds fair, I'll remove the old one |
Signed-off-by: ganyi <pleaplusone.gy@gmail.com>
wangxiyuan
approved these changes
Aug 2, 2025
raindaywhu
added a commit
to raindaywhu/vllm-ascend
that referenced
this pull request
Aug 4, 2025
…to eplb_into_main * 'main' of https://github.com/vllm-project/vllm-ascend: Implementation of simple load balance routing proxy server (vllm-project#1953) (vllm-project#2124)
zzhx1
pushed a commit
to lidenghui1110/vllm-ascend
that referenced
this pull request
Aug 11, 2025
…ect#1953) (vllm-project#2124) ### What this PR does / why we need it? The PR is the cherry-pick from v0.9.1 vllm-project#1953 This PR introduce a new load balance proxy server example implementation for disaggregated pd, which support simple token&kv_cache aware load balance routing strategy for the disaggregated pd system compared with origin round robin toy_proxy. ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? tested on real workload and unittest - vLLM version: v0.10.0 - vLLM main: vllm-project/vllm@ad57f23 --------- Signed-off-by: ganyi <pleaplusone.gy@gmail.com>
zzhx1
pushed a commit
to lidenghui1110/vllm-ascend
that referenced
this pull request
Aug 11, 2025
…ect#1953) (vllm-project#2124) ### What this PR does / why we need it? The PR is the cherry-pick from v0.9.1 vllm-project#1953 This PR introduce a new load balance proxy server example implementation for disaggregated pd, which support simple token&kv_cache aware load balance routing strategy for the disaggregated pd system compared with origin round robin toy_proxy. ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? tested on real workload and unittest - vLLM version: v0.10.0 - vLLM main: vllm-project/vllm@ad57f23 --------- Signed-off-by: ganyi <pleaplusone.gy@gmail.com>
chopper0126
pushed a commit
to chopper0126/vllm-ascend
that referenced
this pull request
Sep 26, 2025
…ect#1953) (vllm-project#2124) ### What this PR does / why we need it? The PR is the cherry-pick from v0.9.1 vllm-project#1953 This PR introduce a new load balance proxy server example implementation for disaggregated pd, which support simple token&kv_cache aware load balance routing strategy for the disaggregated pd system compared with origin round robin toy_proxy. ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? tested on real workload and unittest - vLLM version: v0.10.0 - vLLM main: vllm-project/vllm@ad57f23 --------- Signed-off-by: ganyi <pleaplusone.gy@gmail.com>
Angazenn
pushed a commit
to Angazenn/vllm-ascend
that referenced
this pull request
Oct 21, 2025
…ect#1953) (vllm-project#2124) ### What this PR does / why we need it? The PR is the cherry-pick from v0.9.1 vllm-project#1953 This PR introduce a new load balance proxy server example implementation for disaggregated pd, which support simple token&kv_cache aware load balance routing strategy for the disaggregated pd system compared with origin round robin toy_proxy. ### Does this PR introduce _any_ user-facing change? No ### How was this patch tested? tested on real workload and unittest - vLLM version: v0.10.0 - vLLM main: vllm-project/vllm@ad57f23 --------- Signed-off-by: ganyi <pleaplusone.gy@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
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.
What this PR does / why we need it?
The PR is the cherry-pick from v0.9.1 #1953
This PR introduce a new load balance proxy server example implementation for disaggregated pd, which support simple token&kv_cache aware load balance routing strategy for the disaggregated pd system compared with origin round robin toy_proxy.
Does this PR introduce any user-facing change?
No
How was this patch tested?
tested on real workload and unittest