XiaoxinWang 738bf2b720 support qwen3-next full_decode_only mode. (#3949) ...

### What this PR does / why we need it?
support qwen3-next full_decode_only mode. 
bs=1, max_token=1024
| branch| tps| e2e time|
| --- | --- | --- |
|piecewise  |3.06  | 8.15 |
|fulldecodeonly | 7.2 | 3.47 |

- vLLM version: v0.11.0
- vLLM main:
83f478bb19

Signed-off-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>
Co-authored-by: wangxiaoxin-sherie <wangxiaoxin7@huawei.com>

2025-11-05 08:46:05 +08:00

..

310p

Refactor e2e CI (#2276)

2025-09-02 09:02:22 +08:00

doctests

[CI]: Fix doctest ci for main release (#3451)

2025-10-16 14:38:11 +08:00

models

[Test] Add accuracy test for qwen3-30b-a3b-w8a8 (#3807)

2025-11-04 18:56:31 +08:00

multicard

support qwen3-next full_decode_only mode. (#3949)

2025-11-05 08:46:05 +08:00

nightly

[TEST]Add full graph for multimodal nightly tests (#3968)

2025-11-04 16:47:48 +08:00

pd_disaggreate

ACLgraph enable: Test cases revisions for all features (#3388)

2025-10-17 17:15:19 +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

[E2E][MM] Add e2e tests for InternVL model (#3796)

2025-10-31 15:42:47 +08:00

vllm_interface

Upgrade CANN to 8.3.rc1 (#3945)

2025-11-03 20:21:07 +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

[CI] Optimize nightly CI (#3898)

2025-10-30 23:42:20 +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