[bugfix](CP) Fix and unify the PD request discrimination logic.#5939
Merged
wangxiyuan merged 1 commit intovllm-project:mainfrom Jan 31, 2026
Merged
[bugfix](CP) Fix and unify the PD request discrimination logic.#5939wangxiyuan merged 1 commit intovllm-project:mainfrom
wangxiyuan merged 1 commit intovllm-project:mainfrom
Conversation
pisceskkk
requested review from
MengqingCao,
wangxiyuan and
weijinqian0
as code owners
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. |
pisceskkk
force-pushed
the
fix_main2main
branch
2 times, most recently
from
fadf7ef to
253ce21
Compare
wangxiyuan
approved these changes
Jan 16, 2026
vllm_ascend/attention/utils.py
Outdated
| if query_lens_pcp_full is None else query_lens_pcp_full | ||
| is_prefill = query_lens > decode_threshold | ||
| num_computed_tokens = common_attn_metadata.num_computed_tokens_cpu | ||
| is_prefill = (query_lens > decode_threshold) | (num_computed_tokens == 0) |
pisceskkk
force-pushed
the
fix_main2main
branch
from
253ce21 to
cc430a4
Compare
weiguihua2
added
ready
Contributor
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
pisceskkk
force-pushed
the
fix_main2main
branch
from
cc430a4 to
e794cd8
Compare
pisceskkk
force-pushed
the
fix_main2main
branch
7 times, most recently
from
90a854e to
5cc8fe9
Compare
Contributor
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
pisceskkk
force-pushed
the
fix_main2main
branch
from
5cc8fe9 to
418a43e
Compare
pisceskkk
force-pushed
the
fix_main2main
branch
from
0c76066 to
8e7a058
Compare
pisceskkk
force-pushed
the
fix_main2main
branch
8 times, most recently
from
2c7dbb3 to
85491d8
Compare
Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
chenchuw886
pushed a commit
to chenchuw886/vllm-ascend
that referenced
this pull request
Feb 12, 2026
…-project#5939) ### What this PR does / why we need it? Since the PR (vllm-project/vllm#32118) has modified the criteria for judging Prefill and Decode requests in vLLM, PCPManager needs to synchronize with this standard. As PCPManager involves multiple calculations of PD request counts, this PR attempts to consolidate the related logic and update the PD request count once per batch. ### How was this patch tested? ```bash pytest tests/e2e/multicard/4-cards/long_sequence/test_mtp.py ``` - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@11b6af5 Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com> Signed-off-by: momochenchuw <chenchuw@huawei.com>
Closed
ZRJ026
pushed a commit
to ZRJ026/vllm-ascend
that referenced
this pull request
Feb 28, 2026
…-project#5939) ### What this PR does / why we need it? Since the PR (vllm-project/vllm#32118) has modified the criteria for judging Prefill and Decode requests in vLLM, PCPManager needs to synchronize with this standard. As PCPManager involves multiple calculations of PD request counts, this PR attempts to consolidate the related logic and update the PD request count once per batch. ### How was this patch tested? ```bash pytest tests/e2e/multicard/4-cards/long_sequence/test_mtp.py ``` - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@11b6af5 Signed-off-by: QiuChunshuo <qiuchunshuo@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
…-project#5939) ### What this PR does / why we need it? Since the PR (vllm-project/vllm#32118) has modified the criteria for judging Prefill and Decode requests in vLLM, PCPManager needs to synchronize with this standard. As PCPManager involves multiple calculations of PD request counts, this PR attempts to consolidate the related logic and update the PD request count once per batch. ### How was this patch tested? ```bash pytest tests/e2e/multicard/4-cards/long_sequence/test_mtp.py ``` - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@11b6af5 Signed-off-by: QiuChunshuo <qiuchunshuo@huawei.com>
ZRJ026
pushed a commit
to ZRJ026/vllm-ascend
that referenced
this pull request
Mar 4, 2026
…-project#5939) ### What this PR does / why we need it? Since the PR (vllm-project/vllm#32118) has modified the criteria for judging Prefill and Decode requests in vLLM, PCPManager needs to synchronize with this standard. As PCPManager involves multiple calculations of PD request counts, this PR attempts to consolidate the related logic and update the PD request count once per batch. ### How was this patch tested? ```bash pytest tests/e2e/multicard/4-cards/long_sequence/test_mtp.py ``` - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@11b6af5 Signed-off-by: QiuChunshuo <qiuchunshuo@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
…-project#5939) ### What this PR does / why we need it? Since the PR (vllm-project/vllm#32118) has modified the criteria for judging Prefill and Decode requests in vLLM, PCPManager needs to synchronize with this standard. As PCPManager involves multiple calculations of PD request counts, this PR attempts to consolidate the related logic and update the PD request count once per batch. ### How was this patch tested? ```bash pytest tests/e2e/multicard/4-cards/long_sequence/test_mtp.py ``` - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@11b6af5 Signed-off-by: QiuChunshuo <qiuchunshuo@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?
Since the PR (vllm-project/vllm#32118) has modified the criteria for judging Prefill and Decode requests in vLLM, PCPManager needs to synchronize with this standard. As PCPManager involves multiple calculations of PD request counts, this PR attempts to consolidate the related logic and update the PD request count once per batch.
How was this patch tested?