Wang Kunpeng 1de16ead8e [main][bugfix] Modify the default value of the enable_shared_pert_dp to false (#2457) ...

### What this PR does / why we need it?
enable_shared_pert_dp is currently on by default. This optimization is
currently only valid for deepseek series models. The default opening
affects the accuracy of the qwen series models.
### Does this PR introduce _any_ user-facing change?

### How was this patch tested?
use parameter --additional_config='{"enable_shared_expert_dp": true}'

- vLLM version: v0.10.0
- vLLM main:
d983769c41

Signed-off-by: Wang Kunpeng <1289706727@qq.com>

2025-08-20 20:25:53 +08:00

..

_templates/sections

[doc] add 0.7.3.post1 release note (#1008)

2025-05-29 17:38:34 +08:00

assets

[Doc] Support kimi-k2-w8a8 (#2162)

2025-08-06 19:28:47 +08:00

community

Nominate Mengqing Cao as vllm-ascend maintainer (#2433)

2025-08-19 14:13:54 +08:00

developer_guide

Add ModelRunner_prepare_inputs doc (#1493)

2025-08-18 15:41:24 +08:00

locale/zh_CN/LC_MESSAGES

[Doc]Add Chinese translation for documentation (#1870)

2025-07-21 11:26:27 +08:00

logos

[Doc] Add sphinx build for vllm-ascend (#55)

2025-02-13 18:44:17 +08:00

tutorials

[Doc] Fix quant documentation to make it reproducible (#2277)

2025-08-14 17:19:47 +08:00

user_guide

[main][bugfix] Modify the default value of the enable_shared_pert_dp to false (#2457)

2025-08-20 20:25:53 +08:00

conf.py

[ReleaseNote] Release note of v0.10.0rc1 (#2225)

2025-08-07 14:46:49 +08:00

faqs.md

[Doc] Add container image save/load FAQ for offline environments (#2347)

2025-08-13 16:00:43 +08:00

index.md

[Doc] Update user doc index (#1581)

2025-07-10 14:26:59 +08:00

installation.md

Bump torch version to 2.7.1 (#1562)

2025-08-05 08:43:24 +08:00

quick_start.md

[ReleaseNote] Release note of v0.10.0rc1 (#2225)

2025-08-07 14:46:49 +08:00