[Bug] Fix bug in test_chunked.py #1992
Merged
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
Codecov Report✅ All modified and coverable lines are covered by tests. Additional details and impacted files@@ Coverage Diff @@
## main #1992 +/- ##
=======================================
Coverage 76.09% 76.09%
=======================================
Files 114 114
Lines 13103 13103
=======================================
Hits 9971 9971
Misses 3132 3132
Flags with carried forward coverage won't be shown. Click here to find out more. ☔ View full report in Codecov by Sentry. 🚀 New features to boost your workflow:
|
xleoken
force-pushed
the
patch
branch
6 times, most recently
from
f7b9364 to
b2af312
Compare
xleoken
changed the title
|
cc @Yikun @wangxiyuan take a review when free, thanks |
wangxiyuan
reviewed
Jul 29, 2025
tests/e2e/singlecard/test_chunked.py
Outdated
| vllm_model = LLM(model, long_prefill_token_threshold=4, enforce_eager=True) | ||
| output_chunked = vllm_model.generate(prompts, sampling_params) | ||
| logprobs_chunked = output_chunked.outputs[0].logprobs | ||
| vllm_model = LLM(model, |
There was a problem hiding this comment.
Thanks for this change, can you use VllmRunner instead?
vllm-ascend/tests/e2e/conftest.py
Line 81 in 2da281e
It can cleanup resouce by __exit__ func auomaticlly.
There was a problem hiding this comment.
Thanks for this change, can you use VllmRunner instead?
vllm-ascend/tests/e2e/conftest.py
Line 81 in 2da281e
It can cleanup resouce by
__exit__func auomaticlly.
Nice!!!
xleoken
force-pushed
the
patch
branch
17 times, most recently
from
7bfafb4 to
2e302c4
Compare
xleoken
force-pushed
the
patch
branch
3 times, most recently
from
fb5618d to
ddd761c
Compare
Signed-off-by: xleoken <xleoken@163.com>
|
cc @wangxiyuan @Yikun take a look when free, the ci has passed. |
wangxiyuan
approved these changes
Aug 19, 2025
wangxiaoteng888
pushed a commit
to LCAIZJ/vllm-ascend
that referenced
this pull request
Sep 25, 2025
### What this PR does / why we need it? 1. Remove the return statement, it will always skip following logic. 2. Update `deepseek` to `Qwen2.5-Instruct` for OOM in github e2e test env. 3. Fix the comparison logic ### Does this PR introduce _any_ user-facing change? NO. ### How was this patch tested? Local Test. - vLLM version: v0.10.0 - vLLM main: vllm-project/vllm@0933f9d Signed-off-by: xleoken <xleoken@163.com>
chopper0126
pushed a commit
to chopper0126/vllm-ascend
that referenced
this pull request
Sep 26, 2025
### What this PR does / why we need it? 1. Remove the return statement, it will always skip following logic. 2. Update `deepseek` to `Qwen2.5-Instruct` for OOM in github e2e test env. 3. Fix the comparison logic ### Does this PR introduce _any_ user-facing change? NO. ### How was this patch tested? Local Test. - vLLM version: v0.10.0 - vLLM main: vllm-project/vllm@0933f9d Signed-off-by: xleoken <xleoken@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? 1. Remove the return statement, it will always skip following logic. 2. Update `deepseek` to `Qwen2.5-Instruct` for OOM in github e2e test env. 3. Fix the comparison logic ### Does this PR introduce _any_ user-facing change? NO. ### How was this patch tested? Local Test. - vLLM version: v0.10.0 - vLLM main: vllm-project/vllm@0933f9d Signed-off-by: xleoken <xleoken@163.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
2 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?
Remove the return statement, it will always skip following logic.
Update
deepseektoQwen2.5-Instructfor OOM in github e2e test env.Fix the comparison logic
Does this PR introduce any user-facing change?
NO.
How was this patch tested?
Local Test.