whx 220df60c61 [Model][2/N] Remove deepseek_mtp modeling. (#3561) ...

This PR is step 2 of deepseek model refactoring and removes
deepseek_mtp.

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

---------

Signed-off-by: whx-sjtu <2952154980@qq.com>

2025-10-21 20:17:09 +08:00

..

e2e

remove redundant params in mla_preprocess kernel (#3530)

2025-10-21 19:20:13 +08:00

ut

[Model][2/N] Remove deepseek_mtp modeling. (#3561)

2025-10-21 20:17:09 +08:00

__init__.py

[SpecDecode] Add spec decode support (#500)

2025-04-17 20:16:32 +08:00