[BugFix] Fix npu-cpu offloading interface change bug.#5290
Merged
wangxiyuan merged 4 commits intovllm-project:mainfrom Dec 27, 2025
Merged
[BugFix] Fix npu-cpu offloading interface change bug.#5290wangxiyuan merged 4 commits intovllm-project:mainfrom
wangxiyuan merged 4 commits intovllm-project:mainfrom
Conversation
![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 updates the NPU offloading mechanism to align with a recent interface change in OffloadingSpec, specifically by passing attn_backends through the get_handlers method. The change correctly adapts the method signature and removes the now-obsolete logic for determining attention backends. However, my review identified a significant issue where the attn_backends parameter, while correctly passed to CpuNpuOffloadingHandler, is not utilized within that handler. This indicates an incomplete implementation that could lead to incorrect behavior, as backend-specific logic for KV cache handling might be missing. This should be addressed to ensure the correctness and completeness of the feature.
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. |
whx-sjtu
force-pushed
the
fix_npu_offload
branch
4 times, most recently
from
e70d2f6 to
e765267
Compare
Signed-off-by: whx-sjtu <2952154980@qq.com>
Signed-off-by: whx-sjtu <2952154980@qq.com>
Signed-off-by: whx-sjtu <2952154980@qq.com>
whx-sjtu
force-pushed
the
fix_npu_offload
branch
from
e765267 to
80fdfc3
Compare
zzzzwwjj
approved these changes
Dec 27, 2025
wangxiyuan
approved these changes
Dec 27, 2025
ZRJ026
pushed a commit
to ZRJ026/vllm-ascend
that referenced
this pull request
Feb 28, 2026
) ### What this PR does / why we need it? Last month the interface of `OffloadingSpec` has changed(vllm-project/vllm#27743). This PR fixes this bug and adds e2e test for cpu offloading. ### Does this PR introduce _any_ user-facing change? None ### How was this patch tested? CI passed with new added test. - vLLM version: release/v0.13.0 - vLLM main: vllm-project/vllm@ad32e3e --------- Signed-off-by: whx-sjtu <2952154980@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
) ### What this PR does / why we need it? Last month the interface of `OffloadingSpec` has changed(vllm-project/vllm#27743). This PR fixes this bug and adds e2e test for cpu offloading. ### Does this PR introduce _any_ user-facing change? None ### How was this patch tested? CI passed with new added test. - vLLM version: release/v0.13.0 - vLLM main: vllm-project/vllm@ad32e3e --------- Signed-off-by: whx-sjtu <2952154980@qq.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? Last month the interface of `OffloadingSpec` has changed(vllm-project/vllm#27743). This PR fixes this bug and adds e2e test for cpu offloading. ### Does this PR introduce _any_ user-facing change? None ### How was this patch tested? CI passed with new added test. - vLLM version: release/v0.13.0 - vLLM main: vllm-project/vllm@ad32e3e --------- Signed-off-by: whx-sjtu <2952154980@qq.com> Signed-off-by: zrj026 <zhangrunjiang026@gmail.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?
Last month the interface of
OffloadingSpechas changed(vllm-project/vllm#27743). This PR fixes this bug and adds e2e test for cpu offloading.Does this PR introduce any user-facing change?
None
How was this patch tested?
CI passed with new added test.