[Feat] proxy delay to remove instances#5934
Merged
wangxiyuan merged 1 commit intovllm-project:mainfrom Jan 26, 2026
Merged
Conversation
Contributor
|
👋 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. |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request introduces a mechanism to delay the removal of proxy instances when there are active requests, by 'tainting' them to prevent new traffic. While this is a valuable feature for graceful node isolation, the current implementation has several critical issues related to state management that could lead to incorrect behavior, such as corrupted state and infinite loops. I've identified and provided suggestions for these issues, including a variable shadowing bug, potential for duplicate entries in tainted lists, and failure to clear state after processing. Addressing these points will make the feature robust and reliable.
yuxinshan
force-pushed
the
proxy_add_taint
branch
5 times, most recently
from
0cc2eda to
6934188
Compare
Signed-off-by: yuxinshan <syx_ctyg@126.com>
yuxinshan
force-pushed
the
proxy_add_taint
branch
from
6934188 to
a573bd8
Compare
wangxiyuan
approved these changes
Jan 26, 2026
845473182
pushed a commit
to 845473182/vllm-ascend
that referenced
this pull request
Jan 28, 2026
…to qwen3next_rebase * 'main' of https://github.com/vllm-project/vllm-ascend: (86 commits) [refactor] refactor excute_model and _dymmy_run method (vllm-project#6043) [Refactor] profiler config optimze (vllm-project#6141) [Graph][Fusion] Add MatmulAllReduceAddRMSNorm graph fusion for npugraph_ex. (vllm-project#6006) [UT]: refactoring 310p ops ut (vllm-project#6296) [Refact.]: refactoring 310p-kv cache allocator, align with main branch (vllm-project#6270) [Misc] Removes unnecessary graph size re-initialization (vllm-project#6280) [Main2Main] Upgrade vllm commit to 0123 (vllm-project#6169) [BugFix] Fix wheel package build workflow (vllm-project#6276) [CI][BugFix] Qwen3-Next nightly test fix. (vllm-project#6247) [Doc] quick fix for vllm-ascend version (vllm-project#6278) [Community] Nominate whx-sjtu as maintainer (vllm-project#6268) [Lint] Fix mypy issue to make CI happy (vllm-project#6272) BugFix: Fix moe_load accumulation error in ACL graph mode (vllm-project#6182) [Patch] Remove the patch of ECExampleConnector (vllm-project#5976) [Bugfix] Fix PP+PCP and PP+flashcomm1 bugs (vllm-project#5416) [Feat] proxy delay to remove instances (vllm-project#5934) [CI] Add workfolw_dispatch for nightly image build (vllm-project#6269) [bugfix][npugraph_ex]fix static kernel uninstall issue (vllm-project#6128) [Doc] 310P Documents update (vllm-project#6246) [Feature] Mooncake connector get remote ptp size (vllm-project#5822) ...
starmountain1997
pushed a commit
to starmountain1997/vllm-ascend
that referenced
this pull request
Jan 31, 2026
### What this PR does / why we need it?
For the proxy, we should remove instances when the proxy are not
processing requests.
But sometimes, We need to **isolate** some faulty nodes when a large
number of **requests** are coming in.
So we support to **isolate** faulty nodes by **lowering their priority**
and **deleted** them when the proxy does not process requests.
### Does this PR introduce _any_ user-facing change?
For
`examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py`,
when using `/instances/remove` API to delete the node from the proxy
server:
```txt
curl -X POST http://localhost:9000/instances/remove \
-H "Content-Type: application/json" \
-d '{
"type": "decode",
"instances": "127.0.0.1:8201"
}'
```
There are 2 situations:
* 【New】When the proxy is processing requests, isolate the nodes and
remove them when the proxy is free.
```txt
{"message": "Instances ['127.0.0.1:8201'] are isolated and waiting to be removed.", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101'], "current_decode_instances": ['127.0.0.1:8200', '127.0.0.1:8201']}
```
* When the proxy is free, remove the nodes directly.
```txt
{"message": "remove decode instances: ['127.0.0.1:8201'].", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101'], "current_decode_instances": ['127.0.0.1:8200']}
```
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
vllm-project/vllm@11b6af5
Signed-off-by: yuxinshan <syx_ctyg@126.com>
ZRJ026
pushed a commit
to ZRJ026/vllm-ascend
that referenced
this pull request
Feb 28, 2026
### What this PR does / why we need it?
For the proxy, we should remove instances when the proxy are not
processing requests.
But sometimes, We need to **isolate** some faulty nodes when a large
number of **requests** are coming in.
So we support to **isolate** faulty nodes by **lowering their priority**
and **deleted** them when the proxy does not process requests.
### Does this PR introduce _any_ user-facing change?
For
`examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py`,
when using `/instances/remove` API to delete the node from the proxy
server:
```txt
curl -X POST http://localhost:9000/instances/remove \
-H "Content-Type: application/json" \
-d '{
"type": "decode",
"instances": "127.0.0.1:8201"
}'
```
There are 2 situations:
* 【New】When the proxy is processing requests, isolate the nodes and
remove them when the proxy is free.
```txt
{"message": "Instances ['127.0.0.1:8201'] are isolated and waiting to be removed.", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101'], "current_decode_instances": ['127.0.0.1:8200', '127.0.0.1:8201']}
```
* When the proxy is free, remove the nodes directly.
```txt
{"message": "remove decode instances: ['127.0.0.1:8201'].", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101'], "current_decode_instances": ['127.0.0.1:8200']}
```
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
vllm-project/vllm@11b6af5
Signed-off-by: yuxinshan <syx_ctyg@126.com>
Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>
maoxx241
pushed a commit
to maoxx241/vllm-ascend
that referenced
this pull request
Mar 2, 2026
### What this PR does / why we need it?
For the proxy, we should remove instances when the proxy are not
processing requests.
But sometimes, We need to **isolate** some faulty nodes when a large
number of **requests** are coming in.
So we support to **isolate** faulty nodes by **lowering their priority**
and **deleted** them when the proxy does not process requests.
### Does this PR introduce _any_ user-facing change?
For
`examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py`,
when using `/instances/remove` API to delete the node from the proxy
server:
```txt
curl -X POST http://localhost:9000/instances/remove \
-H "Content-Type: application/json" \
-d '{
"type": "decode",
"instances": "127.0.0.1:8201"
}'
```
There are 2 situations:
* 【New】When the proxy is processing requests, isolate the nodes and
remove them when the proxy is free.
```txt
{"message": "Instances ['127.0.0.1:8201'] are isolated and waiting to be removed.", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101'], "current_decode_instances": ['127.0.0.1:8200', '127.0.0.1:8201']}
```
* When the proxy is free, remove the nodes directly.
```txt
{"message": "remove decode instances: ['127.0.0.1:8201'].", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101'], "current_decode_instances": ['127.0.0.1:8200']}
```
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
vllm-project/vllm@11b6af5
Signed-off-by: yuxinshan <syx_ctyg@126.com>
ZRJ026
pushed a commit
to ZRJ026/vllm-ascend
that referenced
this pull request
Mar 4, 2026
### What this PR does / why we need it?
For the proxy, we should remove instances when the proxy are not
processing requests.
But sometimes, We need to **isolate** some faulty nodes when a large
number of **requests** are coming in.
So we support to **isolate** faulty nodes by **lowering their priority**
and **deleted** them when the proxy does not process requests.
### Does this PR introduce _any_ user-facing change?
For
`examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py`,
when using `/instances/remove` API to delete the node from the proxy
server:
```txt
curl -X POST http://localhost:9000/instances/remove \
-H "Content-Type: application/json" \
-d '{
"type": "decode",
"instances": "127.0.0.1:8201"
}'
```
There are 2 situations:
* 【New】When the proxy is processing requests, isolate the nodes and
remove them when the proxy is free.
```txt
{"message": "Instances ['127.0.0.1:8201'] are isolated and waiting to be removed.", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101'], "current_decode_instances": ['127.0.0.1:8200', '127.0.0.1:8201']}
```
* When the proxy is free, remove the nodes directly.
```txt
{"message": "remove decode instances: ['127.0.0.1:8201'].", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101'], "current_decode_instances": ['127.0.0.1:8200']}
```
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
vllm-project/vllm@11b6af5
Signed-off-by: yuxinshan <syx_ctyg@126.com>
Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>
LCAIZJ
pushed a commit
to LCAIZJ/vllm-ascend
that referenced
this pull request
Mar 7, 2026
### What this PR does / why we need it?
For the proxy, we should remove instances when the proxy are not
processing requests.
But sometimes, We need to **isolate** some faulty nodes when a large
number of **requests** are coming in.
So we support to **isolate** faulty nodes by **lowering their priority**
and **deleted** them when the proxy does not process requests.
### Does this PR introduce _any_ user-facing change?
For
`examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py`,
when using `/instances/remove` API to delete the node from the proxy
server:
```txt
curl -X POST http://localhost:9000/instances/remove \
-H "Content-Type: application/json" \
-d '{
"type": "decode",
"instances": "127.0.0.1:8201"
}'
```
There are 2 situations:
* 【New】When the proxy is processing requests, isolate the nodes and
remove them when the proxy is free.
```txt
{"message": "Instances ['127.0.0.1:8201'] are isolated and waiting to be removed.", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101'], "current_decode_instances": ['127.0.0.1:8200', '127.0.0.1:8201']}
```
* When the proxy is free, remove the nodes directly.
```txt
{"message": "remove decode instances: ['127.0.0.1:8201'].", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101'], "current_decode_instances": ['127.0.0.1:8200']}
```
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
vllm-project/vllm@11b6af5
Signed-off-by: yuxinshan <syx_ctyg@126.com>
jiangyunfan1
pushed a commit
to jiangyunfan1/vllm-ascend
that referenced
this pull request
Apr 9, 2026
### What this PR does / why we need it?
For the proxy, we should remove instances when the proxy are not
processing requests.
But sometimes, We need to **isolate** some faulty nodes when a large
number of **requests** are coming in.
So we support to **isolate** faulty nodes by **lowering their priority**
and **deleted** them when the proxy does not process requests.
### Does this PR introduce _any_ user-facing change?
For
`examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py`,
when using `/instances/remove` API to delete the node from the proxy
server:
```txt
curl -X POST http://localhost:9000/instances/remove \
-H "Content-Type: application/json" \
-d '{
"type": "decode",
"instances": "127.0.0.1:8201"
}'
```
There are 2 situations:
* 【New】When the proxy is processing requests, isolate the nodes and
remove them when the proxy is free.
```txt
{"message": "Instances ['127.0.0.1:8201'] are isolated and waiting to be removed.", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101'], "current_decode_instances": ['127.0.0.1:8200', '127.0.0.1:8201']}
```
* When the proxy is free, remove the nodes directly.
```txt
{"message": "remove decode instances: ['127.0.0.1:8201'].", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101'], "current_decode_instances": ['127.0.0.1:8200']}
```
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
vllm-project/vllm@11b6af5
Signed-off-by: yuxinshan <syx_ctyg@126.com>
yangzhe-2026
pushed a commit
to yangzhe-2026/vllm-ascend
that referenced
this pull request
May 6, 2026
### What this PR does / why we need it?
For the proxy, we should remove instances when the proxy are not
processing requests.
But sometimes, We need to **isolate** some faulty nodes when a large
number of **requests** are coming in.
So we support to **isolate** faulty nodes by **lowering their priority**
and **deleted** them when the proxy does not process requests.
### Does this PR introduce _any_ user-facing change?
For
`examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py`,
when using `/instances/remove` API to delete the node from the proxy
server:
```txt
curl -X POST http://localhost:9000/instances/remove \
-H "Content-Type: application/json" \
-d '{
"type": "decode",
"instances": "127.0.0.1:8201"
}'
```
There are 2 situations:
* 【New】When the proxy is processing requests, isolate the nodes and
remove them when the proxy is free.
```txt
{"message": "Instances ['127.0.0.1:8201'] are isolated and waiting to be removed.", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101'], "current_decode_instances": ['127.0.0.1:8200', '127.0.0.1:8201']}
```
* When the proxy is free, remove the nodes directly.
```txt
{"message": "remove decode instances: ['127.0.0.1:8201'].", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101'], "current_decode_instances": ['127.0.0.1:8200']}
```
### How was this patch tested?
- vLLM version: v0.13.0
- vLLM main:
vllm-project/vllm@11b6af5
Signed-off-by: yuxinshan <syx_ctyg@126.com>
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
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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?
For the proxy, we should remove instances when the proxy are not processing requests.
But sometimes, We need to isolate some faulty nodes when a large number of requests are coming in.
So we support to isolate faulty nodes by lowering their priority and deleted them when the proxy does not process requests.
Does this PR introduce any user-facing change?
For
examples/disaggregated_prefill_v1/load_balance_proxy_server_example.py, when using/instances/removeAPI to delete the node from the proxy server:curl -X POST http://localhost:9000/instances/remove \ -H "Content-Type: application/json" \ -d '{ "type": "decode", "instances": "127.0.0.1:8201" }'There are 2 situations:
{"message": "Instances ['127.0.0.1:8201'] are isolated and waiting to be removed.", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101'], "current_decode_instances": ['127.0.0.1:8200', '127.0.0.1:8201']}{"message": "remove decode instances: ['127.0.0.1:8201'].", "current_prefill_instances": ['127.0.0.1:8100', '127.0.0.1:8101'], "current_decode_instances": ['127.0.0.1:8200']}How was this patch tested?