[Bugfix] fix bug of pcp+mtp+async scheduler#5994
Merged
weijinqian0 merged 3 commits intovllm-project:mainfrom Jan 20, 2026
Merged
[Bugfix] fix bug of pcp+mtp+async scheduler#5994weijinqian0 merged 3 commits intovllm-project:mainfrom
weijinqian0 merged 3 commits intovllm-project:mainfrom
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 aims to fix a bug related to the combination of PCP, MTP, and asynchronous scheduling. The changes involve passing additional scheduling information to the PCPManager and correcting the logic for calculating sequence lengths and updating input IDs in asynchronous speculative decoding scenarios. The core logic change in pcp_utils.py appears to correctly handle the state transfer between iterations for async scheduling. However, I've found a critical issue in the test case added to verify this fix, where a duplicated parameter prevents the test from running with the intended configuration.
| max_num_batched_tokens=1024, | ||
| enable_expert_parallel=True, | ||
| block_size=128, | ||
| async_scheduling=True, |
Contributor
There was a problem hiding this comment.
The async_scheduling parameter is specified twice for the VllmRunner. The value True set on this line will be overridden by async_scheduling=False on line 79. As a result, this test case does not run with asynchronous scheduling enabled, and therefore does not validate the bugfix for the async scenario. To fix this, please remove the redundant async_scheduling=False on line 79.
wangxiyuan
approved these changes
Jan 19, 2026
wangxiyuan
added
ready
Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
weijinqian0
approved these changes
Jan 20, 2026
yiz-liu
pushed a commit
that referenced
this pull request
Jan 20, 2026
### What this PR does / why we need it? Fixed the issue where the PCP and MTP services could not be started due to asynchronous scheduling. After the pcp, mtp, and asynchronous scheduling functions are enabled, the service is suspended because of a shape mismatch after a curl request is sent. This PR resolves this issue. PR for the main branch: #5994 ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? --------- Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
845473182
pushed a commit
to 845473182/vllm-ascend
that referenced
this pull request
Jan 21, 2026
…to FIA_rebase * 'main' of https://github.com/vllm-project/vllm-ascend: (24 commits) add dispath_ffn_combine_bf16 (vllm-project#5866) [BugFix] Fix input parameter bug of dispatch_gmm_combine_decode[RFC: issue 5476] (vllm-project#5932) [1/N][Feat] Xlite Qwen3 MoE Support (vllm-project#5951) [Bugfix] Fix setting of `speculative_config.enforce_eager` for dsv32 (vllm-project#5945) [bugfix][mm] change get_num_encoder_tokens to get_num_encoder_embeds in recompute_schedule.py (vllm-project#5132) [Bugfix] fix pcp qwen full graph FIA bug (vllm-project#6037) [Bugfix]Fixed precision issues caused by pooled request pooling (vllm-project#6049) 【main】【bugfix】Resolved memory deallocation failure in the pooling layer under re-computation workloads. (vllm-project#6045) [main][Bugfix] Fixed an problem related to embeddings sharing (vllm-project#5967) [Feature]refactor the npugraph_ex config, support online-infer with static kernel (vllm-project#5775) [CI][Lint] Show lint diff on failure (vllm-project#5956) [CI] Add wait logic for each individual case (vllm-project#6036) [CI] Add DeepSeek-V3.2-W8A8 nightly ci test (vllm-project#4633) model runner v2 support triton of penalty (vllm-project#5854) [Docs][Model] Support Qwen3-VL-Embedding & Qwen3-VL-Reranker (vllm-project#6034) [Tests] move qwen3 performance test from nightly to e2e (vllm-project#5980) [Bugfix] fix bug of pcp+mtp+async scheduler (vllm-project#5994) [Main2Main] Upgrade vllm commit to releases/v0.14.0 (vllm-project#5988) [Ops] Add layernorm for qwen3Next (vllm-project#5765) [Doc] Add layer_sharding additional config for DeepSeek-V3.2-W8A8 (vllm-project#5921) ...
starmountain1997
pushed a commit
to starmountain1997/vllm-ascend
that referenced
this pull request
Jan 31, 2026
### What this PR does / why we need it? Fixed the issue where the PCP and MTP services could not be started due to asynchronous scheduling. After the pcp, mtp, and asynchronous scheduling functions are enabled, the service is suspended because of a shape mismatch after a curl request is sent. This PR resolves this issue. ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@2c24bc6 --------- Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
starmountain1997
pushed a commit
to starmountain1997/vllm-ascend
that referenced
this pull request
Jan 31, 2026
### What this PR does / why we need it? Fixed the issue where the PCP and MTP services could not be started due to asynchronous scheduling. After the pcp, mtp, and asynchronous scheduling functions are enabled, the service is suspended because of a shape mismatch after a curl request is sent. This PR resolves this issue. PR for the main branch: vllm-project#5994 ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? --------- Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
starmountain1997
pushed a commit
to starmountain1997/vllm-ascend
that referenced
this pull request
Jan 31, 2026
### What this PR does / why we need it? Fixed the issue where the PCP and MTP services could not be started due to asynchronous scheduling. After the pcp, mtp, and asynchronous scheduling functions are enabled, the service is suspended because of a shape mismatch after a curl request is sent. This PR resolves this issue. ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@2c24bc6 --------- Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
tangtiangu
pushed a commit
to tangtiangu/jiusi-vllm-ascend
that referenced
this pull request
Feb 24, 2026
### What this PR does / why we need it? Fixed the issue where the PCP and MTP services could not be started due to asynchronous scheduling. After the pcp, mtp, and asynchronous scheduling functions are enabled, the service is suspended because of a shape mismatch after a curl request is sent. This PR resolves this issue. PR for the main branch: vllm-project#5994 ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? --------- Signed-off-by: weiguihua2 <weiguihua2@huawei.com>
tangtiangu
pushed a commit
to tangtiangu/jiusi-vllm-ascend
that referenced
this pull request
Feb 24, 2026
### What this PR does / why we need it? Fixed the issue where the PCP and MTP services could not be started due to asynchronous scheduling. After the pcp, mtp, and asynchronous scheduling functions are enabled, the service is suspended because of a shape mismatch after a curl request is sent. This PR resolves this issue. PR for the main branch: vllm-project#5994 ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? --------- Signed-off-by: weiguihua2 <weiguihua2@huawei.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? Fixed the issue where the PCP and MTP services could not be started due to asynchronous scheduling. After the pcp, mtp, and asynchronous scheduling functions are enabled, the service is suspended because of a shape mismatch after a curl request is sent. This PR resolves this issue. ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@2c24bc6 --------- Signed-off-by: weiguihua2 <weiguihua2@huawei.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? Fixed the issue where the PCP and MTP services could not be started due to asynchronous scheduling. After the pcp, mtp, and asynchronous scheduling functions are enabled, the service is suspended because of a shape mismatch after a curl request is sent. This PR resolves this issue. ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@2c24bc6 --------- Signed-off-by: weiguihua2 <weiguihua2@huawei.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? Fixed the issue where the PCP and MTP services could not be started due to asynchronous scheduling. After the pcp, mtp, and asynchronous scheduling functions are enabled, the service is suspended because of a shape mismatch after a curl request is sent. This PR resolves this issue. ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@2c24bc6 --------- Signed-off-by: weiguihua2 <weiguihua2@huawei.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? Fixed the issue where the PCP and MTP services could not be started due to asynchronous scheduling. After the pcp, mtp, and asynchronous scheduling functions are enabled, the service is suspended because of a shape mismatch after a curl request is sent. This PR resolves this issue. ### Does this PR introduce _any_ user-facing change? ### How was this patch tested? - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@2c24bc6 --------- Signed-off-by: weiguihua2 <weiguihua2@huawei.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
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?
Fixed the issue where the PCP and MTP services could not be started due to asynchronous scheduling.
After the pcp, mtp, and asynchronous scheduling functions are enabled, the service is suspended because of a shape mismatch after a curl request is sent. This PR resolves this issue.
Does this PR introduce any user-facing change?
How was this patch tested?