[CI] Add accuracy test for Qwen2.5-VL-3B-Instruct #766
Conversation
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
zhangxinyuehfad
force-pushed
the
zxy_accuracy_ci
branch
6 times, most recently
from
4fc2290 to
04f5971
Compare
zhangxinyuehfad
force-pushed
the
zxy_accuracy_ci
branch
4 times, most recently
from
2d97020 to
30a4c65
Compare
|
let's merge this after CI is refactored. Thanks. |
zhangxinyuehfad
force-pushed
the
zxy_accuracy_ci
branch
7 times, most recently
from
089037a to
8121193
Compare
done |
Yikun
reviewed
Jun 3, 2025
tests/long_term/test_accuracy.py
Outdated
Comment on lines
61
to
70
| # wrap prompts in a chat-style template. | ||
| APPLY_CHAT_TEMPLATE = { | ||
| "Qwen/Qwen2.5-0.5B-Instruct": False, | ||
| "Qwen/Qwen2.5-VL-3B-Instruct": True | ||
| } | ||
| # Few-shot examples handling as multi-turn dialogues. | ||
| FEWSHOT_AS_MULTITURN = { | ||
| "Qwen/Qwen2.5-0.5B-Instruct": False, | ||
| "Qwen/Qwen2.5-VL-3B-Instruct": True | ||
| } |
There was a problem hiding this comment.
shoudn't these be generate from MODEL_TYPE?
tests/long_term/test_accuracy.py
Outdated
Comment on lines
102
to
98
| if model == "Qwen/Qwen2.5-VL-3B-Instruct" and os.getenv( | ||
| "VLLM_USE_V1") == "1": | ||
| pytest.skip( | ||
| "Qwen2.5-VL-3B-Instruct is not supported when VLLM_USE_V1=1") |
There was a problem hiding this comment.
should be a decrator after @pytest.mark.parametrize .
and seems all vllm-vlm should be skipped.
There was a problem hiding this comment.
only need skip model Qwen2.5-VL-3B-Instruct where VLLM_USE_V1=1, and it run ok when VLLM_USE_V1=0
76 tasks
zhangxinyuehfad
force-pushed
the
zxy_accuracy_ci
branch
from
8121193 to
ac70438
Compare
Yikun
reviewed
Jun 4, 2025
| VLLM_WORKER_MULTIPROC_METHOD: spawn | ||
| run: | | ||
| if [[ "${{ matrix.os }}" == "linux-arm64-npu-1" ]]; then | ||
| pytest -sv tests/long_term/test_accuracy.py |
There was a problem hiding this comment.
Suggested change
| pytest -sv tests/long_term/test_accuracy.py |
| VLLM_USE_V1: 0 | ||
| run: | | ||
| if [[ "${{ matrix.os }}" == "linux-arm64-npu-1" ]]; then | ||
| pytest -sv tests/long_term/test_accuracy.py |
There was a problem hiding this comment.
Suggested change
| pytest -sv tests/long_term/test_accuracy.py |
zhangxinyuehfad
force-pushed
the
zxy_accuracy_ci
branch
from
ac70438 to
9930c96
Compare
Yikun
added
long-term-test
|
Need trigger long term test after main CI fixed: #905 |
|
This pull request has conflicts, please resolve those before we can evaluate the pull request. |
zhangxinyuehfad
force-pushed
the
zxy_accuracy_ci
branch
from
9930c96 to
13bd8d3
Compare
Yikun
added
long-term-test
Signed-off-by: hfadzxy <starmoon_zhang@163.com>
zhangxinyuehfad
force-pushed
the
zxy_accuracy_ci
branch
from
13bd8d3 to
064f779
Compare
wangxiyuan
approved these changes
Jun 5, 2025
chopper0126
pushed a commit
to chopper0126/vllm-ascend
that referenced
this pull request
Oct 16, 2025
### What this PR does / why we need it? Add accuracy test for Qwen2.5-VL-3B-Instruct Signed-off-by: hfadzxy <starmoon_zhang@163.com>
Angazenn
pushed a commit
to Angazenn/vllm-ascend
that referenced
this pull request
Oct 21, 2025
### What this PR does / why we need it? Add accuracy test for Qwen2.5-VL-3B-Instruct Signed-off-by: hfadzxy <starmoon_zhang@163.com>
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?
Add accuracy test for Qwen2.5-VL-3B-Instruct
Does this PR introduce any user-facing change?
How was this patch tested?