drslark 0fb1dc43a1 [BugFix][main] Adapted Qwen3-Next-MTP to chunked prefill (#4770) ...

### What this PR does / why we need it?
The pad `-1` modification is from
https://github.com/vllm-project/vllm/pull/25743.

It still has bugs for batched chunked prefill.

- vLLM version: v0.12.0
- vLLM main:
ad32e3e19c

Signed-off-by: drslark <slarksblood@qq.com>
Co-authored-by: Mengqing Cao <cmq0113@163.com>

2025-12-10 22:54:24 +08:00

..

310p

Drop torchair (#4814)

2025-12-10 09:20:40 +08:00

doctests

[Doc] Recover installation doc to use pip install (#4109)

2025-11-11 09:25:44 +08:00

models

[CI]Cleanup accurary test (#4861)

2025-12-10 14:13:56 +08:00

multicard

[BugFix][main] Adapted Qwen3-Next-MTP to chunked prefill (#4770)

2025-12-10 22:54:24 +08:00

nightly

[Nightly] Optimize nightly online test logger info (#4798)

2025-12-10 09:24:19 +08:00

pd_disaggreate

[P/D][main]Offline the llmdatadist connector related parts of the code and files. (#4780)

2025-12-09 22:36:43 +08:00

prompts

[CI/UT] Add test for chunk prefill and prefix cache on v1/AscendScheduler (#1505)

2025-07-02 16:57:03 +08:00

singlecard

[Model] Support pooling models (#3122)

2025-12-10 11:37:57 +08:00

vllm_interface

[main]Upgrade cann to 8.3rc2 (#4350)

2025-11-28 14:06:01 +08:00

__init__.py

[Test] Clean up duplicate test for ascend scheduler (#1819)

2025-07-16 17:57:48 +08:00

common.sh

Increase doctest timeout to 300s and time print (#3041)

2025-09-19 20:26:00 +08:00

conftest.py

[Model] Support pooling models (#3122)

2025-12-10 11:37:57 +08:00

model_utils.py

[Misc] Clean up useless patch (#3320)

2025-10-09 14:07:26 +08:00

run_disagg_pd.sh

[CI] Fix PD job (#1129)

2025-06-09 16:34:41 +08:00

run_doctests.sh

Increase doctest timeout to 300s and time print (#3041)

2025-09-19 20:26:00 +08:00

utils.py

[Test] Remove VLLM_USE_V1 in example and tests (#1733)

2025-07-15 12:49:57 +08:00