Skip to content

Conversation

@songshanhu07
Copy link
Contributor

@songshanhu07 songshanhu07 commented Jun 12, 2025

What this PR does / why we need it?

1.add static EPLB unit test
2.fix bug: Tensor cannot be directly judged by if statements

Does this PR introduce any user-facing change?

How was this patch tested?

Run the unit test.

Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: songshanhu07 <1763685535@qq.com>
@jianzs
Copy link
Collaborator

jianzs commented Jun 14, 2025

Please add e2e tests to ensure the feature continues to function correctly during future changes.

@MengqingCao
Copy link
Collaborator

Overall ltgm, plz move it to proper path under tests/ut/

…to main

* 'main' of https://github.com/vllm-project/vllm-ascend: (22 commits)
  [Bugfix] Remove cuda related lines and add additional pip mirror (#1252)
  [refactor] Refactoring AscendFusedMoE (#1229)
  [Doc] Refactor and init user story page  (#1224)
  [Doctest] add installation doctest (#1179)
  [DP][V1] Fix rank set in DP scenario & Bump torch-npu version to 2.5.1.post1.dev20250528 (#1235)
  Fix the device error when using ray as vllm-acend backend (#884)
  [CI] Add unit test framework (#1201)
  [Build] Speedup image build (#1216)
  [CI] Make e2e test to be preemptible and simple (#1217)
  Waiting for BMM NZ support(Improve TPOP 2ms performance)  (#1131)
  [Doc] fix VLLM_USE_V1 value in graph mode docs (#1226)
  vllm-ascend support chunked prefill (#1172)
  [CI/UT][Graph] Add ut for torchair graph mode (#1103)
  Add ShouJian Zheng (@jianzs) as vLLM Ascend maintainer (#1203)
  [CI] Recover ut for ascend scheduler only in ci of v1. (#1180)
  Support multistream of MLA vector operations (#1135)
  [Doc] Add Referer header for CANN package download url. (#1192)
  [fix] fix bug in 1p1d disaggregated_prefill example (#1184)
  [CI][Benchmark] Add qwen2.5-7b test (#1104)
  [CI][Benchmark] Add new model and v1 test to perf benchmarks (#1099)
  ...
Sync with upstream main branch# the commit.
Signed-off-by: songshanhu07 <1763685535@qq.com>
@songshanhu07 songshanhu07 changed the title add static EPLB unit test static EPLB fix bug, add unit test Jun 17, 2025
Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: songshanhu07 <1763685535@qq.com>
@github-actions github-actions bot added the documentation Improvements or additions to documentation label Jun 18, 2025
Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: songshanhu07 <1763685535@qq.com>
@@ -1,2 +1,2 @@
pytest-asyncio

pytest-mock
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Suggested change
pytest-mock
pytest >= 6.0
pytest-mock

openai
pytest >= 6.0
pytest-asyncio
pytest-mock
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Let's add -r requirements-test.txt in line3 and move this to requirements-test.txt instead

Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

we could do this later in your e2e test pr

@ganyi1996ppo ganyi1996ppo merged commit ebb2a70 into vllm-project:main Jun 18, 2025
20 checks passed
@@ -0,0 +1,146 @@
# fused moe ops test will hit the infer_schema error, we need add the patch
Copy link
Collaborator

@wangxiyuan wangxiyuan Jun 19, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

for ut, I don't think use assert is not a good way. Please use unittest lib instead.

shiyuan680 pushed a commit to raindaywhu/vllm-ascend that referenced this pull request Jul 7, 2025
<!--  Thanks for sending a pull request!

BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html

-->
<!--
- Please clarify what changes you are proposing. The purpose of this
section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster
reviews in your PR.

- Please clarify why the changes are needed. For instance, the use case
and bug description.

- Fixes #
-->
1.add static EPLB unit test
2.fix bug: Tensor cannot be directly judged by if statements
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->

<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->
Run the unit test.

---------

Signed-off-by: songshanhu07 <1763685535@qq.com>
ganyi1996ppo pushed a commit that referenced this pull request Jul 8, 2025
### What this PR does / why we need it?

[cherry-pick master->
0.9.1-dev](#1186)
1.add static EPLB unit test
2.fix bug: Tensor cannot be directly judged by if statements
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?
Run the unit test.

Signed-off-by: songshanhu07 <1763685535@qq.com>
wanghanqingLYT pushed a commit to raindaywhu/vllm-ascend that referenced this pull request Jul 9, 2025
…project#1667)

### What this PR does / why we need it?

[cherry-pick master->
0.9.1-dev](vllm-project#1186)
1.add static EPLB unit test
2.fix bug: Tensor cannot be directly judged by if statements
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?
Run the unit test.

Signed-off-by: songshanhu07 <1763685535@qq.com>
weijinqian0 pushed a commit to weijinqian0/vllm-ascend that referenced this pull request Jul 9, 2025
…project#1667)

### What this PR does / why we need it?

[cherry-pick master->
0.9.1-dev](vllm-project#1186)
1.add static EPLB unit test
2.fix bug: Tensor cannot be directly judged by if statements
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?
Run the unit test.

Signed-off-by: songshanhu07 <1763685535@qq.com>
Signed-off-by: weijinqian_v1 <weijinqian@huawei.com>
@Yikun Yikun changed the title static EPLB fix bug, add unit test Fix static EPLB log2phy condition and improve unit test Aug 5, 2025
chopper0126 pushed a commit to chopper0126/vllm-ascend that referenced this pull request Oct 16, 2025
<!--  Thanks for sending a pull request!

BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html

-->
### What this PR does / why we need it?
<!--
- Please clarify what changes you are proposing. The purpose of this
section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster
reviews in your PR.

- Please clarify why the changes are needed. For instance, the use case
and bug description.

- Fixes #
-->
1.add static EPLB unit test
2.fix bug: Tensor cannot be directly judged by if statements
### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->

### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->
Run the unit test.

---------

Signed-off-by: songshanhu07 <1763685535@qq.com>
Angazenn pushed a commit to Angazenn/vllm-ascend that referenced this pull request Oct 21, 2025
<!--  Thanks for sending a pull request!

BEFORE SUBMITTING, PLEASE READ
https://docs.vllm.ai/en/latest/contributing/overview.html

-->
### What this PR does / why we need it?
<!--
- Please clarify what changes you are proposing. The purpose of this
section is to outline the changes and how this PR fixes the issue.
If possible, please consider writing useful notes for better and faster
reviews in your PR.

- Please clarify why the changes are needed. For instance, the use case
and bug description.

- Fixes #
-->
1.add static EPLB unit test
2.fix bug: Tensor cannot be directly judged by if statements
### Does this PR introduce _any_ user-facing change?
<!--
Note that it means *any* user-facing change including all aspects such
as API, interface or other behavior changes.
Documentation-only updates are not considered user-facing changes.
-->

### How was this patch tested?
<!--
CI passed with new added/existing test.
If it was tested in a way different from regular unit tests, please
clarify how you tested step by step, ideally copy and paste-able, so
that other reviewers can test and check, and descendants can verify in
the future.
If tests were not added, please describe why they were not added and/or
why it was difficult to add.
-->
Run the unit test.

---------

Signed-off-by: songshanhu07 <1763685535@qq.com>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

documentation Improvements or additions to documentation module:quantization module:tests

Projects

None yet

Development

Successfully merging this pull request may close these issues.

5 participants