Skip to content

[Bugfix][V1] Fix deepseek with v1 #958

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Merged
merged 1 commit into from
May 29, 2025
Merged

[Bugfix][V1] Fix deepseek with v1 #958

merged 1 commit into from
May 29, 2025

Conversation

@MengqingCao
Copy link
Collaborator

@MengqingCao MengqingCao commented May 26, 2025 •
edited
Loading

What this PR does / why we need it?

Fix deepseek with v1, this error is introdeced by #945. and this pr fix the block table of mla

How was this patch tested?

CI passed with new addedtest.

@MengqingCao
Copy link
Collaborator Author

@wangxiyuan This pr fixes the broken ci on v1+deepseek, now it is ready for review

@MengqingCao
[Bugfix][V1] Fix deepseek with v1
7fd38bf 
Signed-off-by: Mengqing Cao <cmq0113@163.com>
@Yikun
Copy link
Collaborator

Yikun commented May 28, 2025 

FAILED tests/singlecard/test_offline_inference.py::test_models[5-half-Qwen/Qwen2.5-0.5B-Instruct] - pydantic_core._pydantic_core.ValidationError: 2 validation errors for DeviceConfig
device.literal['auto','cuda','neuron','cpu','tpu','xpu','hpu']
  Input should be 'auto', 'cuda', 'neuron', 'cpu', 'tpu', 'xpu' or 'hpu' [type=literal_error, input_value='npu', input_type=str]

Unrelated CI failed, caused by vllm-project/vllm@4c2b38c and try to fix it on: vllm-project/vllm#18843

@wangxiyuan wangxiyuan merged commit cc74b97 into vllm-project:main May 29, 2025
17 of 22 checks passed
raindaywhu added a commit to raindaywhu/vllm-ascend that referenced this pull request May 30, 2025
@raindaywhu
Merge branch 'main' of https://github.com/raindaywhu/vllm-ascend into…
fd7b81e 
… main

* 'main' of https://github.com/raindaywhu/vllm-ascend:
  [aclgraph] implentment NPUPiecewiseBackend to enable aclgraph (vllm-project#836)
  [Bugfix][V1] Fix deepseek with v1 (vllm-project#958)
  [Perf] Refactor tensor disposal logic to reduce memory usage (vllm-project#966)
@MengqingCao MengqingCao deleted the fix branch May 30, 2025 02:53
David9857 pushed a commit to David9857/vllm-ascend that referenced this pull request Jun 3, 2025
@MengqingCao @David9857
[Bugfix][V1] Fix deepseek with v1 (vllm-project#958)
86df4cf 
### What this PR does / why we need it?
Fix deepseek with v1, this error is introdeced by
vllm-project#945. and this pr fix
the block table of mla

### How was this patch tested?
CI passed with new addedtest.

Signed-off-by: Mengqing Cao <cmq0113@163.com>
chopper0126 pushed a commit to chopper0126/vllm-ascend that referenced this pull request Oct 16, 2025
@MengqingCao
[Bugfix][V1] Fix deepseek with v1 (vllm-project#958)
e498e5a 
### What this PR does / why we need it?
Fix deepseek with v1, this error is introdeced by
vllm-project#945. and this pr fix
the block table of mla

### How was this patch tested?
CI passed with new addedtest.

Signed-off-by: Mengqing Cao <cmq0113@163.com>
Angazenn pushed a commit to Angazenn/vllm-ascend that referenced this pull request Oct 21, 2025
@MengqingCao @Angazenn
[Bugfix][V1] Fix deepseek with v1 (vllm-project#958)
a83f921 
### What this PR does / why we need it?
Fix deepseek with v1, this error is introdeced by
vllm-project#945. and this pr fix
the block table of mla

### How was this patch tested?
CI passed with new addedtest.

Signed-off-by: Mengqing Cao <cmq0113@163.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Reviewers

@Yikun Yikun Yikun approved these changes

@wangxiyuan wangxiyuan wangxiyuan approved these changes

Assignees

No one assigned

Labels

module:tests

Projects

None yet

Milestone

No milestone

Development

Successfully merging this pull request may close these issues.

3 participants

@MengqingCao @Yikun @wangxiyuan