zhangxinyuehfad
1cd27da5fb
[Test] Remove VLLM_USE_V1 in accuracy test ( #1739 )
...
### What this PR does / why we need it?
Remove VLLM_USE_V1 in accuracy test
Signed-off-by: hfadzxy <starmoon_zhang@163.com >
2025-07-11 15:29:11 +08:00
Yikun Jiang
e4e9ea02ab
Upgrade vLLM version to v0.9.2 ( #1652 )
...
### What this PR does / why we need it?
This patch upgrade vLLM version to v0.9.2, this patch didn't remove the
v0.9.1 compatible code to easy review.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
- vLLM version: v0.9.1
- vLLM main:
14601f5fbahttps://github.com/vllm-project/vllm-ascend/actions/runs/16121612087
Signed-off-by: Yikun Jiang <yikunkero@gmail.com >
2025-07-08 14:18:17 +08:00
zhangxinyuehfad
14373f65d7
[Test] Remove V0 accuracy test and enable MoE and VL test on V1 ( #1574 )
...
### What this PR does / why we need it?
Update accuracy test
1. remove accuarcy report on V0
2. add parallel and execution mode
3. add Qwen/Qwen3-30B-A3B and remove Qwen/Qwen2.5-7B-Instruct
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
CI passed
Signed-off-by: hfadzxy <starmoon_zhang@163.com >
2025-07-06 11:10:19 +08:00
zhangxinyuehfad
4e910186de
[CI/UT] Unify model usage via ModelScope in CI ( #1207 )
...
### What this PR does / why we need it?
Unify Model Usage via ModelScope
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
CI passed
Signed-off-by: hfadzxy <starmoon_zhang@163.com >
2025-07-04 10:52:17 +08:00
dependabot[bot]
790c810bf7
Bump actions/github-script from 6 to 7 ( #1519 )
...
Bumps [actions/github-script](https://github.com/actions/github-script )
from 6 to 7.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/actions/github-script/releases ">actions/github-script's
releases</a>.</em></p>
<blockquote>
<h2>v7.0.0</h2>
<h2>What's Changed</h2>
<ul>
<li>Add base-url option by <a
href="https://github.com/robandpdx "><code>@robandpdx</code></a> in <a
href="https://redirect.github.com/actions/github-script/pull/429 ">actions/github-script#429</a></li>
<li>Expose async-function argument type by <a
href="https://github.com/viktorlott "><code>@viktorlott</code></a> in <a
href="https://redirect.github.com/actions/github-script/pull/402 ">actions/github-script#402</a>,
see for details <a
href="https://github.com/actions/github-script#use-scripts-with-jsdoc-support ">https://github.com/actions/github-script#use-scripts-with-jsdoc-support </a></li>
<li>Update dependencies and use Node 20 by <a
href="https://github.com/joshmgross "><code>@joshmgross</code></a> in <a
href="https://redirect.github.com/actions/github-script/pull/425 ">actions/github-script#425</a></li>
</ul>
<h2>New Contributors</h2>
<ul>
<li><a
href="https://github.com/navarroaxel "><code>@navarroaxel</code></a>
made their first contribution in <a
href="https://redirect.github.com/actions/github-script/pull/285 ">actions/github-script#285</a></li>
<li><a href="https://github.com/robandpdx "><code>@robandpdx</code></a>
made their first contribution in <a
href="https://redirect.github.com/actions/github-script/pull/429 ">actions/github-script#429</a></li>
<li><a
href="https://github.com/viktorlott "><code>@viktorlott</code></a> made
their first contribution in <a
href="https://redirect.github.com/actions/github-script/pull/402 ">actions/github-script#402</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/actions/github-script/compare/v6.4.1...v7.0.0 ">https://github.com/actions/github-script/compare/v6.4.1...v7.0.0 </a></p>
<h2>v6.4.1</h2>
<h2>What's Changed</h2>
<ul>
<li>Add <code>@octokit/plugin-request-log</code>, to produce debug
output for requests by <a
href="https://github.com/mjpieters "><code>@mjpieters</code></a> in <a
href="https://redirect.github.com/actions/github-script/pull/358 ">actions/github-script#358</a></li>
<li>fix input handling by <a
href="https://github.com/mjpieters "><code>@mjpieters</code></a> in <a
href="https://redirect.github.com/actions/github-script/pull/357 ">actions/github-script#357</a></li>
<li>Remove unused dependencies by <a
href="https://github.com/mjpieters "><code>@mjpieters</code></a> in <a
href="https://redirect.github.com/actions/github-script/pull/356 ">actions/github-script#356</a></li>
<li>Default debug to current runner debug state by <a
href="https://github.com/mjpieters "><code>@mjpieters</code></a> in <a
href="https://redirect.github.com/actions/github-script/pull/363 ">actions/github-script#363</a></li>
</ul>
<h2>New Contributors</h2>
<ul>
<li><a href="https://github.com/mjpieters "><code>@mjpieters</code></a>
made their first contribution in <a
href="https://redirect.github.com/actions/github-script/pull/358 ">actions/github-script#358</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/actions/github-script/compare/v6.4.0...v6.4.1 ">https://github.com/actions/github-script/compare/v6.4.0...v6.4.1 </a></p>
<h2>v6.4.0</h2>
<h2>What's Changed</h2>
<ul>
<li>Bump json5 from 2.1.3 to 2.2.3 by <a
href="https://github.com/dependabot "><code>@dependabot</code></a> in <a
href="https://redirect.github.com/actions/github-script/pull/319 ">actions/github-script#319</a></li>
<li>Bump minimatch from 3.0.4 to 3.1.2 by <a
href="https://github.com/dependabot "><code>@dependabot</code></a> in <a
href="https://redirect.github.com/actions/github-script/pull/320 ">actions/github-script#320</a></li>
<li>Add node-fetch by <a
href="https://github.com/danmichaelo "><code>@danmichaelo</code></a> in
<a
href="https://redirect.github.com/actions/github-script/pull/321 ">actions/github-script#321</a></li>
</ul>
<h2>New Contributors</h2>
<ul>
<li><a href="https://github.com/jongwooo "><code>@jongwooo</code></a>
made their first contribution in <a
href="https://redirect.github.com/actions/github-script/pull/313 ">actions/github-script#313</a></li>
<li><a
href="https://github.com/austinvazquez "><code>@austinvazquez</code></a>
made their first contribution in <a
href="https://redirect.github.com/actions/github-script/pull/306 ">actions/github-script#306</a></li>
<li><a
href="https://github.com/danmichaelo "><code>@danmichaelo</code></a>
made their first contribution in <a
href="https://redirect.github.com/actions/github-script/pull/321 ">actions/github-script#321</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/actions/github-script/compare/v6.3.3...v6.4.0 ">https://github.com/actions/github-script/compare/v6.3.3...v6.4.0 </a></p>
<h2>v6.3.3</h2>
<h2>What's Changed</h2>
<ul>
<li>Update <code>@actions/glob</code> to 0.3.0 by <a
href="https://github.com/nineinchnick "><code>@nineinchnick</code></a>
in <a
href="https://redirect.github.com/actions/github-script/pull/279 ">actions/github-script#279</a></li>
</ul>
<h2>New Contributors</h2>
<ul>
<li><a
href="https://github.com/nineinchnick "><code>@nineinchnick</code></a>
made their first contribution in <a
href="https://redirect.github.com/actions/github-script/pull/279 ">actions/github-script#279</a></li>
</ul>
<p><strong>Full Changelog</strong>: <a
href="https://github.com/actions/github-script/compare/v6.3.2...v6.3.3 ">https://github.com/actions/github-script/compare/v6.3.2...v6.3.3 </a></p>
<h2>v6.3.2</h2>
<h2>What's Changed</h2>
<ul>
<li>Update <code>@actions/core</code> to 1.10.0 by <a
href="https://github.com/rentziass "><code>@rentziass</code></a> in <a
href="https://redirect.github.com/actions/github-script/pull/295 ">actions/github-script#295</a></li>
</ul>
<!-- raw HTML omitted -->
</blockquote>
<p>... (truncated)</p>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="60a0d83039https://redirect.github.com/actions/github-script/issues/440 ">#440</a>
from actions/joshmgross/v7.0.1</li>
<li><a
href="b7fb2001b412e22ed06bhttps://redirect.github.com/actions/github-script/issues/439 ">#439</a>
from actions/joshmgross/avoid-setting-base-url</li>
<li><a
href="d319f8f5b5e69ef5462fhttps://redirect.github.com/actions/github-script/issues/425 ">#425</a>
from actions/joshmgross/node-20</li>
<li><a
href="ee0914b839d6fc56f33b384d6cf58184724927e384903f5182https://github.com/actions/github-script/compare/v6...v7 ">compare
view</a></li>
</ul>
</details>
<br />
[](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores )
Dependabot will resolve any conflicts with this PR as long as you don't
alter it yourself. You can also trigger a rebase manually by commenting
`@dependabot rebase`.
[//]: # (dependabot-automerge-start)
[//]: # (dependabot-automerge-end)
---
<details>
<summary>Dependabot commands and options</summary>
<br />
You can trigger Dependabot actions by commenting on this PR:
- `@dependabot rebase` will rebase this PR
- `@dependabot recreate` will recreate this PR, overwriting any edits
that have been made to it
- `@dependabot merge` will merge this PR after your CI passes on it
- `@dependabot squash and merge` will squash and merge this PR after
your CI passes on it
- `@dependabot cancel merge` will cancel a previously requested merge
and block automerging
- `@dependabot reopen` will reopen this PR if it is closed
- `@dependabot close` will close this PR and stop Dependabot recreating
it. You can achieve the same result by closing it manually
- `@dependabot show <dependency name> ignore conditions` will show all
of the ignore conditions of the specified dependency
- `@dependabot ignore this major version` will close this PR and stop
Dependabot creating any more for this major version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this minor version` will close this PR and stop
Dependabot creating any more for this minor version (unless you reopen
the PR or upgrade to it yourself)
- `@dependabot ignore this dependency` will close this PR and stop
Dependabot creating any more for this dependency (unless you reopen the
PR or upgrade to it yourself)
</details>
Signed-off-by: dependabot[bot] <support@github.com >
Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
2025-06-30 16:04:41 +08:00
zhangxinyuehfad
06ccce1ddf
[FOLLOWUP] fix name and format in accuracy test ( #1288 ) ( #1435 )
...
### What this PR does / why we need it?
fix accuracy test:
1. fix accuracy report
like:https://vllm-ascend--1429.org.readthedocs.build/en/1429/developer_guide/evaluation/accuracy_report/Qwen2.5-7B-Instruct-V0.html
2. fix create pr for report
Signed-off-by: hfadzxy <starmoon_zhang@163.com >
2025-06-26 00:26:54 +08:00
zhangxinyuehfad
0060886a37
[CI]Update accuracy report test ( #1288 )
...
### What this PR does / why we need it?
Update accuracy report test
1. Add Record commit hashes and GitHub links for both vllm and
vllm-ascend in accuracy reports
2. Add accuracy result verification checks to ensure output correctness
3. Creat PR via forked repository workflow
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
dense-accuracy-test:
https://github.com/vllm-project/vllm-ascend/actions/runs/15745619485
create pr via forked repository workflow:
https://github.com/zhangxinyuehfad/vllm-ascend/actions/runs/15747013719/job/44385134080
accuracy report pr:
https://github.com/vllm-project/vllm-ascend/pull/1292
Currently, the accuracy report used is old and needs to be merged into
pr, retest, update new report, then close #1292 .
Signed-off-by: hfadzxy <starmoon_zhang@163.com >
2025-06-25 14:10:34 +08:00
Yikun Jiang
a95afc011e
[CI] Enable merge trigger unit test and accuracy test schedule job ( #1345 )
...
### What this PR does / why we need it?
- Enable merge trigger unit test and accuracy test schedule job
- Pin lm-eval==0.4.8 to resovle Qwen3 8B accuracy
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
CI passed
Signed-off-by: Yikun Jiang <yikunkero@gmail.com >
2025-06-22 17:21:57 +08:00
Mengqing Cao
96fa7ff63b
[DP][V1] Fix rank set in DP scenario & Bump torch-npu version to 2.5.1.post1.dev20250528 ( #1235 )
...
### What this PR does / why we need it?
1. Fix rank set in DP scenario. The new poc version of torch-npu support
setting `ASCEND_RT_VISIBLE_DEVICES` dynamically, thus we could use the
rank set in `DPEngineCoreProc` directly instead of calculating local
rank across dp by hand in the patched `_init_data_parallel`
Closes: https://github.com/vllm-project/vllm-ascend/issues/1170
2. Bump torch-npu version to 2.5.1.post1.dev20250528
Closes: https://github.com/vllm-project/vllm-ascend/pull/1242
Closes: https://github.com/vllm-project/vllm-ascend/issues/1232
### How was this patch tested?
CI passed with new added test.
---------
Signed-off-by: MengqingCao <cmq0113@163.com >
Signed-off-by: Icey <1790571317@qq.com >
Co-authored-by: Icey <1790571317@qq.com >
2025-06-16 23:09:53 +08:00
wangxiyuan
4f5964420e
[CI] Upgrade vllm to 0.9.1 ( #1165 )
...
1. upgrade vllm to 0.9.1. 0.9.0 is not supported for main branch now.
keep doc to 0.9.0 until we release the first 0.9.1 release.
2. disable V0 test for PR
3. move actionlint check to lint job
Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com >
2025-06-11 16:33:11 +08:00
zhangxinyuehfad
e68e81f2ce
[CI] Make accuarcy CI and report work ( #1078 )
...
### What this PR does / why we need it?
Make accuarcy CI and report work
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
Manaully review
Signed-off-by: hfadzxy <starmoon_zhang@163.com >
2025-06-10 14:35:44 +08:00
Yikun Jiang
9e855b70be
Adjust concurrency group for each npu workflow ( #1068 )
...
### What this PR does / why we need it?
Adjust concurrency group for each npu workflow
- for pd and benchmarks share the static-08-01, so only one job can runs
on
- other job one PR/schedule should have only 1 job runs
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
CI passed
Signed-off-by: Yikun Jiang <yikunkero@gmail.com >
2025-06-05 09:17:04 +08:00
Yikun Jiang
f24375f318
Enable accuracy test for PR labeled with "*accuracy-test" ( #1040 )
...
### What this PR does / why we need it?
This PR enable accuracy test for PR labeled with "*accuracy-test" and
workflow_dispatch.
Only one model test running for each type test to reduce excution time.
- The dense test costs about `25mins` to complete (gsm8k 7mins, ~mmlu
3h24mins,~ cEval 18mins)
- The vl test costs about `40mins` to complete
In futute, we might consider enable all job test as nightly schedule
job.
Below is mainly changes:
- the dense/vl accuracy test will be triggered by lableling
`accuracy-test` and `ready-for-test`
- the dense accuracy test will be triggered by lableling
`dense-accuracy-test` and `ready-for-test`
- the vl accuracy test will be triggered by lableling `vl-accuracy-test`
and `ready-for-test`
- accuracy test will also be triggered by workflow_dispatch
- Support V1 and V0 for qwen and V0 for VL
For PR test we also generate summary in test summary.
### Does this PR introduce _any_ user-facing change?
No
### How was this patch tested?
- CI passed with accuracy-test label
- Preview:
https://github.com/vllm-project/vllm-ascend/actions/runs/15407628722?pr=1040
Closes: https://github.com/vllm-project/vllm-ascend/pull/953
---------
Signed-off-by: hfadzxy <starmoon_zhang@163.com >
Signed-off-by: Yikun Jiang <yikunkero@gmail.com >
Co-authored-by: hfadzxy <starmoon_zhang@163.com >
2025-06-03 15:38:13 +08:00
hfadzxy
4a2505f81f
[accuracy test]Update cann version and huggingface-hub version for Qwen3 ( #823 )
...
### What this PR does / why we need it?
1. update cann version to 8.1.0 for multimodal
2. fix huggingface-hub version to adapt to qwen3
3. change Qwen3-8B to Qwen-8B-Base,
Signed-off-by: hfadzxy <starmoon_zhang@163.com >
2025-05-12 19:12:48 +08:00
hfadzxy
affca6f348
[Test] Add accuracy test report workflow ( #542 )
...
### What this PR does / why we need it?
1. Provide accuracy test report for development branch release.
2. Models and datasets for accuracy test：
| Model | datasets |
|---------------------------- | --------------------------- |
| Qwen2.5-7B-Instruct | ceval-val, gsm8k, mmlu |
| Qwen3-8B | ceval-val, gsm8k, mmlu |
| Llama-3.1-8B-Instruct | ceval-val, gsm8k, mmlu |
| Qwen2.5-VL-7B-Instruct | mmmu_val |
### Does this PR introduce _any_ user-facing change?
This PR will display the accuracy test report of the release versionin
docs/source/developer_guide/accuracy_report。
Qwen2.5-7B-Instruct.md
Qwen3-8B.md
Llama-3.1-8B-Instruct.md
Qwen2.5-VL-7B-Instruct .md
Signed-off-by: hfadzxy <starmoon_zhang@163.com >
2025-04-30 14:53:58 +08:00
