roger-lcc 37cc307322 register apply_repetition_penalties_ in custom_op (#110) ...

* fix qwen2_vl for 0.11.0

* register apply_repetition_penalties_ in custom_op

---------

Co-authored-by: luochencheng <luochencheng@baidu.com>

2026-01-13 20:22:14 +08:00

..

compilation

提交vllm0.11.0开发分支

2025-12-10 17:51:24 +08:00

csrc

Initial commit for vLLM-Kunlun Plugin

2025-12-10 12:05:39 +08:00

distributed

提交vllm0.11.0开发分支

2025-12-10 17:51:24 +08:00

models

[Bugs] fix qwen2_vl for 0.11.0 (#94)

2026-01-09 15:05:40 +08:00

ops

[Bugfix] fix can not import compressed_tensors (#87)

2026-01-07 11:32:10 +08:00

patches

提交vllm0.11.0开发分支

2025-12-10 17:51:24 +08:00

platforms

[Feature] support deepseek v3/r1/v3.2 (#78)

2026-01-05 22:55:35 +08:00

tests

Initial commit for vLLM-Kunlun Plugin

2025-12-10 12:05:39 +08:00

v1

Merge pull request #106 from baoqian426/enable-full-cudagraph-deepseek

2026-01-13 09:57:56 +08:00

worker

提交vllm0.11.0开发分支

2025-12-10 17:51:24 +08:00

__init__.py

[Feature] DeepSeek Support MTP

2026-01-06 21:37:21 +08:00

utils.py

提交vllm0.11.0开发分支

2025-12-10 17:51:24 +08:00

vllm_utils_wrapper.py

register apply_repetition_penalties_ in custom_op (#110)

2026-01-13 20:22:14 +08:00