[Redo] #26368 #28771
Merged
[Redo] #26368 #28771
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
DarkLight1337
added
the
ready
DarkLight1337
requested review from
ApostaC,
WoosukKwon,
alexm-redhat,
heheda12345,
njhill,
robertgshaw2-redhat and
ywang96
as code owners
5 tasks
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
Contributor
There was a problem hiding this comment.
Code Review
This pull request correctly fixes a type mismatch for sampled_token_ids in _mock_execute_model by using np.random.randint to generate a list[np.ndarray]. However, this change introduces a source of non-determinism in the tests because a seed for numpy.random is not set. My review includes a comment to address this to ensure test reproducibility.
DarkLight1337
changed the title
Jialin
approved these changes
Nov 15, 2025
Collaborator
Jialin
left a comment
Jialin
left a comment
There was a problem hiding this comment.
Appreciate your help for the fix forward.
njhill
approved these changes
Nov 15, 2025
Member
|
IMO we should force-merge a revert per our agreed policy now. I'm trying to fix a bunch of other things and this is quite disruptive. We can iron out the test issues in the PR branch |
Member
|
I opened #28773 |
Member
Author
|
Alright, originally I thought this was a simple fix 😅 |
…or output tokens for GC optimization (vllm-project#26368) Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk>
DarkLight1337
force-pushed
the
fix-other-test
branch
from
37eed6c to
d40ec3b
Compare
DarkLight1337
requested review from
22quinn,
benchislett,
houseroad and
luccafong
as code owners
Member
Author
|
I have rebased this PR to redo the original commit, we can merge it if the tests pass |
Member
Author
|
Test passes now |
geodavic
pushed a commit
to geodavic/vllm
that referenced
this pull request
Nov 16, 2025
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com> Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk> Co-authored-by: Jialin Ouyang <Jialin.Ouyang@gmail.com> Signed-off-by: George D. Torres <gdavtor@gmail.com>
1 task
bwasti
pushed a commit
to bwasti/vllm
that referenced
this pull request
Nov 17, 2025
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com> Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk> Co-authored-by: Jialin Ouyang <Jialin.Ouyang@gmail.com> Signed-off-by: Bram Wasti <bwasti@meta.com>
Jialin
added a commit
to Jialin/vllm
that referenced
this pull request
Nov 20, 2025
This reverts commit 98b4d38. Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
Jialin
added a commit
to Jialin/vllm
that referenced
this pull request
Nov 21, 2025
This reverts commit 98b4d38. Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
vllm-bot
pushed a commit
that referenced
this pull request
Nov 21, 2025
LuminolT
pushed a commit
to LuminolT/vllm
that referenced
this pull request
Nov 21, 2025
…#29121) Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com> Signed-off-by: LuminolT <lumischen01@gmail.com>
ywang96
pushed a commit
to ywang96/vllm
that referenced
this pull request
Nov 23, 2025
…#29121) Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
lpapavassiliou
pushed a commit
to lpapavassiliou/vllm
that referenced
this pull request
Nov 24, 2025
…#29121) Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
RunkaiTao
pushed a commit
to RunkaiTao/vllm
that referenced
this pull request
Nov 24, 2025
…#29121) Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com> Signed-off-by: Runkai Tao <rt572@physics.rutgers.edu>
wangxiyuan
added a commit
to vllm-project/vllm-ascend
that referenced
this pull request
Nov 26, 2025
Bump vLLM version to v0.11.2 What's broken and changed by vLLM: 1. structured_output is broken by vllm-project/vllm#26866 2. get_mrope_input_positions is broken by vllm-project/vllm#28399 3. graph mode is broken by vllm-project/vllm#25110 we'll upgrade torch to 2.8 to fix the problem later 4. embedding is broken by vllm-project/vllm#27583 5. `get_attn_backend_cls` and attention backend is broken are broken by vllm-project/vllm#28534 6. spec decode is broken by vllm-project/vllm#28771 7. sp feature is broken by vllm-project/vllm#27126 8. mtp is broken by vllm-project/vllm#27922 9. lora is broken by vllm-project/vllm#21068 10. execute_model is broken by vllm-project/vllm#26866 11. `VLLM_DISABLE_SHARED_EXPERTS_STREAM` env is broken by vllm-project/vllm#28159 12. kv cahe is broken by vllm-project/vllm#27753 13. dp is broken by vllm-project/vllm#25110 What's broken and changed by ourself: 1. qwen vl is broken by vllm-project/vllm#28455 We'll remove model files in the future to avoid this kind of error 2. Engine core is broken by vllm-project/vllm#23691 We'll remove the patch file in the future. 3. Ascend scheduler is broken by vllm-project/vllm#28733 We'll remove ascend scheudler later. 4. qwen3-next is broken by vllm-project/vllm#28083 We'll remove model files in the future to avoid this kind of error 5. qwen vl is broken by vllm-project/vllm#27764. We'll remove model files in the future Known issue: 1. ray doesn't work 2. the accuracy of qwen3-next is not correct 3. qwen3-vl is broken 4. prefix cache+ ascend scheduler + deepseek v2 lite is broken. Co-authored-by: MengqingCao <cmq0113@163.com> Co-authored-by: hfadzxy <starmoon_zhang@163.com> Co-authored-by: leo-pony <nengjunma@outlook.com> Co-authored-by: 22dimensions <waitingwind@foxmail.com> Co-authored-by: shen-shanshan <467638484@qq.com> - vLLM version: v0.11.2 --------- Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com> Signed-off-by: MengqingCao <cmq0113@163.com> Signed-off-by: hfadzxy <starmoon_zhang@163.com> Signed-off-by: leo-pony <nengjunma@outlook.com> Co-authored-by: MengqingCao <cmq0113@163.com> Co-authored-by: hfadzxy <starmoon_zhang@163.com> Co-authored-by: leo-pony <nengjunma@outlook.com>
Kurumi5210
pushed a commit
to lidenghui1110/vllm-ascend
that referenced
this pull request
Nov 26, 2025
Bump vLLM version to v0.11.2 What's broken and changed by vLLM: 1. structured_output is broken by vllm-project/vllm#26866 2. get_mrope_input_positions is broken by vllm-project/vllm#28399 3. graph mode is broken by vllm-project/vllm#25110 we'll upgrade torch to 2.8 to fix the problem later 4. embedding is broken by vllm-project/vllm#27583 5. `get_attn_backend_cls` and attention backend is broken are broken by vllm-project/vllm#28534 6. spec decode is broken by vllm-project/vllm#28771 7. sp feature is broken by vllm-project/vllm#27126 8. mtp is broken by vllm-project/vllm#27922 9. lora is broken by vllm-project/vllm#21068 10. execute_model is broken by vllm-project/vllm#26866 11. `VLLM_DISABLE_SHARED_EXPERTS_STREAM` env is broken by vllm-project/vllm#28159 12. kv cahe is broken by vllm-project/vllm#27753 13. dp is broken by vllm-project/vllm#25110 What's broken and changed by ourself: 1. qwen vl is broken by vllm-project/vllm#28455 We'll remove model files in the future to avoid this kind of error 2. Engine core is broken by vllm-project/vllm#23691 We'll remove the patch file in the future. 3. Ascend scheduler is broken by vllm-project/vllm#28733 We'll remove ascend scheudler later. 4. qwen3-next is broken by vllm-project/vllm#28083 We'll remove model files in the future to avoid this kind of error 5. qwen vl is broken by vllm-project/vllm#27764. We'll remove model files in the future Known issue: 1. ray doesn't work 2. the accuracy of qwen3-next is not correct 3. qwen3-vl is broken 4. prefix cache+ ascend scheduler + deepseek v2 lite is broken. Co-authored-by: MengqingCao <cmq0113@163.com> Co-authored-by: hfadzxy <starmoon_zhang@163.com> Co-authored-by: leo-pony <nengjunma@outlook.com> Co-authored-by: 22dimensions <waitingwind@foxmail.com> Co-authored-by: shen-shanshan <467638484@qq.com> - vLLM version: v0.11.2 --------- Signed-off-by: wangxiyuan <wangxiyuan1007@gmail.com> Signed-off-by: MengqingCao <cmq0113@163.com> Signed-off-by: hfadzxy <starmoon_zhang@163.com> Signed-off-by: leo-pony <nengjunma@outlook.com> Co-authored-by: MengqingCao <cmq0113@163.com> Co-authored-by: hfadzxy <starmoon_zhang@163.com> Co-authored-by: leo-pony <nengjunma@outlook.com> Signed-off-by: Kurumi5210 <Jaychou1620@Gmail.com>
bringlein
pushed a commit
to bringlein/vllm
that referenced
this pull request
Nov 26, 2025
Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com> Signed-off-by: DarkLight1337 <tlleungac@connect.ust.hk> Co-authored-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
bringlein
pushed a commit
to bringlein/vllm
that referenced
this pull request
Nov 26, 2025
…#29121) Signed-off-by: Jialin Ouyang <Jialin.Ouyang@gmail.com>
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
4 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.
Purpose
Redo of #26368 that passes V1 Tests
Test Plan
Test Result
Essential Elements of an Effective PR Description Checklist
supported_models.mdandexamplesfor a new model.