zhaozx-cn bf87606932 [Feat] Shared expert dp for deepseek and deepseek_mtp (#3495) ...

### What this PR does / why we need it?
shared expert dp for deepseek and deepseek_mtp, could be combined with
sp to improve performance.

### How was this patch tested?

- vLLM version: v0.11.0rc3
- vLLM main: https://github.com/vllm-project/vllm/commit/v0.11.0

---------

Signed-off-by: zhaozx-cn <zhaozx2116@163.com>
Co-authored-by: realliujiaxu <realliujiaxu@163.com>

2025-10-17 15:06:37 +08:00

..

__init__.py

ut:add ut for qwen2_5_vl_without_padding.py (#1988)

2025-07-25 14:12:44 +08:00

conftest.py

[MoE] [Refactor] Combine common_fused_moe and fused_moe (#3176)

2025-10-09 14:12:46 +08:00

test_deepseek_mtp.py

[Feat] Shared expert dp for deepseek and deepseek_mtp (#3495)

2025-10-17 15:06:37 +08:00

test_deepseek_v2.py

[Feat] Flash comm allgher ep (#3334)

2025-10-15 19:36:32 +08:00

test_qwen2_5_vl_without_padding.py

[Bugfix] Fix qwen2.5-vl-without-padding (#2623)

2025-09-03 14:38:55 +08:00

test_qwen2_5_vl.py

[CI] Upgrade vLLM version (#3139)

2025-09-25 07:36:51 +08:00

test_qwen2_vl.py

ut:add ut for qwen2_vl.py (#2096)

2025-07-30 22:31:47 +08:00