[Bugfix] Fix the input constraints checks for the mlapo and bmm_transpose operators#5764
Merged
wangxiyuan merged 1 commit intovllm-project:mainfrom Jan 16, 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 correctly fixes the input constraint checks for the mlapo and bmm_transpose operators by replacing the has_prefill flag with a direct check on the number of input tokens. This change addresses a bug and improves the correctness of operator selection. The associated code simplification by removing the has_prefill logic is also a good improvement. However, this refactoring appears to break existing unit tests, which must be updated to reflect the changes.
rjg-lyh
force-pushed
the
pr-bugfix-token-limit
branch
from
ad41eba to
56d8584
Compare
Contributor
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
rjg-lyh
force-pushed
the
pr-bugfix-token-limit
branch
from
56d8584 to
c2a4d80
Compare
weijinqian0
approved these changes
Jan 15, 2026
rjg-lyh
force-pushed
the
pr-bugfix-token-limit
branch
from
c2a4d80 to
d2c4609
Compare
rjg-lyh
added
ready
whx-sjtu
reviewed
Jan 15, 2026
rjg-lyh
force-pushed
the
pr-bugfix-token-limit
branch
2 times, most recently
from
fd0113d to
186e916
Compare
linfeng-yuan
approved these changes
Jan 16, 2026
…pose operators Signed-off-by: rjg-lyh <1318825571@qq.com>
rjg-lyh
force-pushed
the
pr-bugfix-token-limit
branch
from
186e916 to
dbea536
Compare
wangxiyuan
approved these changes
Jan 16, 2026
Closed
rjg-lyh
added a commit
to rjg-lyh/vllm-ascend
that referenced
this pull request
Jan 21, 2026
…bmm_transpose operators (vllm-project#5764) This PR fix the input constraints checks for the mlapo and bmm_transpose operators. No. CI passed with new added/existing test. - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@2f4e654 64K/3K，1P1D，bs=32 before this pr: TPOT 29ms, TTFT 47s，TPS 606 token/s after this pr: TPOT 29ms, TTFT 48s，TPS 636 token/s Signed-off-by: rjg-lyh <1318825571@qq.com>
rjg-lyh
added a commit
to rjg-lyh/vllm-ascend
that referenced
this pull request
Jan 21, 2026
…bmm_transpose operators (vllm-project#5764) This PR fix the input constraints checks for the mlapo and bmm_transpose operators. No. CI passed with new added/existing test. - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@2f4e654 64K/3K，1P1D，bs=32 before this pr: TPOT 29ms, TTFT 47s，TPS 606 token/s after this pr: TPOT 29ms, TTFT 48s，TPS 636 token/s Signed-off-by: rjg-lyh <1318825571@qq.com>
rjg-lyh
added a commit
to rjg-lyh/vllm-ascend
that referenced
this pull request
Jan 21, 2026
…bmm_transpose operators (vllm-project#5764) This PR fix the input constraints checks for the mlapo and bmm_transpose operators. No. CI passed with new added/existing test. - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@2f4e654 64K/3K，1P1D，bs=32 before this pr: TPOT 29ms, TTFT 47s，TPS 606 token/s after this pr: TPOT 29ms, TTFT 48s，TPS 636 token/s Signed-off-by: rjg-lyh <1318825571@qq.com>
rjg-lyh
added a commit
to rjg-lyh/vllm-ascend
that referenced
this pull request
Jan 22, 2026
…bmm_transpose operators (vllm-project#5764) This PR fix the input constraints checks for the mlapo and bmm_transpose operators. No. CI passed with new added/existing test. - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@2f4e654 64K/3K，1P1D，bs=32 before this pr: TPOT 29ms, TTFT 47s，TPS 606 token/s after this pr: TPOT 29ms, TTFT 48s，TPS 636 token/s Signed-off-by: rjg-lyh <1318825571@qq.com>
wangxiyuan
pushed a commit
that referenced
this pull request
Jan 22, 2026
…bmm_transpose operators (#5764) (#6088) ### What this PR does / why we need it? This PR cherry-pick #5764 This PR fix the input constraints checks for the mlapo and bmm_transpose operators. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? CI passed with new added/existing test. Signed-off-by: rjg-lyh <1318825571@qq.com>
845473182
pushed a commit
to 845473182/vllm-ascend
that referenced
this pull request
Jan 22, 2026
…lm-ascend into FIA_v0.13.0 * 'releases/v0.13.0' of https://github.com/vllm-project/vllm-ascend: [EPLB] Config Rename wrapper (vllm-project#6111) [v0.13.0][Bugfix] Fix the input constraints checks for the mlapo and bmm_transpose operators (vllm-project#5764) (vllm-project#6088)
starmountain1997
pushed a commit
to starmountain1997/vllm-ascend
that referenced
this pull request
Jan 31, 2026
…pose operators (vllm-project#5764) ### What this PR does / why we need it? This PR fix the input constraints checks for the mlapo and bmm_transpose operators. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? CI passed with new added/existing test. - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@2f4e654 ### Perf 64K/3K，1P1D，bs=32 before this pr: TPOT 29ms, TTFT 47s，TPS 606 token/s after this pr: TPOT 29ms, TTFT 48s，TPS 636 token/s Signed-off-by: rjg-lyh <1318825571@qq.com>
starmountain1997
pushed a commit
to starmountain1997/vllm-ascend
that referenced
this pull request
Jan 31, 2026
…bmm_transpose operators (vllm-project#5764) (vllm-project#6088) ### What this PR does / why we need it? This PR cherry-pick vllm-project#5764 This PR fix the input constraints checks for the mlapo and bmm_transpose operators. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? CI passed with new added/existing test. Signed-off-by: rjg-lyh <1318825571@qq.com>
starmountain1997
pushed a commit
to starmountain1997/vllm-ascend
that referenced
this pull request
Jan 31, 2026
…pose operators (vllm-project#5764) ### What this PR does / why we need it? This PR fix the input constraints checks for the mlapo and bmm_transpose operators. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? CI passed with new added/existing test. - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@2f4e654 ### Perf 64K/3K，1P1D，bs=32 before this pr: TPOT 29ms, TTFT 47s，TPS 606 token/s after this pr: TPOT 29ms, TTFT 48s，TPS 636 token/s Signed-off-by: rjg-lyh <1318825571@qq.com>
tangtiangu
pushed a commit
to tangtiangu/jiusi-vllm-ascend
that referenced
this pull request
Feb 24, 2026
…bmm_transpose operators (vllm-project#5764) (vllm-project#6088) ### What this PR does / why we need it? This PR cherry-pick vllm-project#5764 This PR fix the input constraints checks for the mlapo and bmm_transpose operators. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? CI passed with new added/existing test. Signed-off-by: rjg-lyh <1318825571@qq.com>
tangtiangu
pushed a commit
to tangtiangu/jiusi-vllm-ascend
that referenced
this pull request
Feb 24, 2026
…bmm_transpose operators (vllm-project#5764) (vllm-project#6088) ### What this PR does / why we need it? This PR cherry-pick vllm-project#5764 This PR fix the input constraints checks for the mlapo and bmm_transpose operators. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? CI passed with new added/existing test. Signed-off-by: rjg-lyh <1318825571@qq.com>
ZRJ026
pushed a commit
to ZRJ026/vllm-ascend
that referenced
this pull request
Feb 28, 2026
…pose operators (vllm-project#5764) ### What this PR does / why we need it? This PR fix the input constraints checks for the mlapo and bmm_transpose operators. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? CI passed with new added/existing test. - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@2f4e654 ### Perf 64K/3K，1P1D，bs=32 before this pr: TPOT 29ms, TTFT 47s，TPS 606 token/s after this pr: TPOT 29ms, TTFT 48s，TPS 636 token/s Signed-off-by: rjg-lyh <1318825571@qq.com> Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>
maoxx241
pushed a commit
to maoxx241/vllm-ascend
that referenced
this pull request
Mar 2, 2026
…pose operators (vllm-project#5764) ### What this PR does / why we need it? This PR fix the input constraints checks for the mlapo and bmm_transpose operators. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? CI passed with new added/existing test. - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@2f4e654 ### Perf 64K/3K，1P1D，bs=32 before this pr: TPOT 29ms, TTFT 47s，TPS 606 token/s after this pr: TPOT 29ms, TTFT 48s，TPS 636 token/s Signed-off-by: rjg-lyh <1318825571@qq.com>
ZRJ026
pushed a commit
to ZRJ026/vllm-ascend
that referenced
this pull request
Mar 4, 2026
…pose operators (vllm-project#5764) ### What this PR does / why we need it? This PR fix the input constraints checks for the mlapo and bmm_transpose operators. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? CI passed with new added/existing test. - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@2f4e654 ### Perf 64K/3K，1P1D，bs=32 before this pr: TPOT 29ms, TTFT 47s，TPS 606 token/s after this pr: TPOT 29ms, TTFT 48s，TPS 636 token/s Signed-off-by: rjg-lyh <1318825571@qq.com> Signed-off-by: zrj026 <zhangrunjiang026@gmail.com>
LCAIZJ
pushed a commit
to LCAIZJ/vllm-ascend
that referenced
this pull request
Mar 7, 2026
…pose operators (vllm-project#5764) ### What this PR does / why we need it? This PR fix the input constraints checks for the mlapo and bmm_transpose operators. ### Does this PR introduce _any_ user-facing change? No. ### How was this patch tested? CI passed with new added/existing test. - vLLM version: v0.13.0 - vLLM main: vllm-project/vllm@2f4e654 ### Perf 64K/3K，1P1D，bs=32 before this pr: TPOT 29ms, TTFT 47s，TPS 606 token/s after this pr: TPOT 29ms, TTFT 48s，TPS 636 token/s Signed-off-by: rjg-lyh <1318825571@qq.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
5 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?
This PR fix the input constraints checks for the mlapo and bmm_transpose operators.
Does this PR introduce any user-facing change?
No.
How was this patch tested?
CI passed with new added/existing test.
Perf
64K/3K，1P1D，bs=32
before this pr:
TPOT 29ms, TTFT 47s，TPS 606 token/s
after this pr:
TPOT 29ms, TTFT 48s，TPS 636 token/s