fromck 0ce5f1a3f7 Add kernels to optimize RoPE and the decoding stage (#143) ...

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

2026-01-23 10:29:52 +08:00

..

backends

提交vllm0.11.0开发分支

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

__init__.py

Initial commit for vLLM-Kunlun Plugin

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

flashmla.py

Add kernels to optimize RoPE and the decoding stage (#143)

2026-01-23 10:29:52 +08:00

layer.py

提交vllm0.11.0开发分支

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

merge_attn_states.py

longcontext chunk make attention crash, fix it (#117)

2026-01-17 18:38:23 +08:00

mla.py

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

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