sunlei1024 d5a3c5c933 feat: add draft_logprobs for Speculative Decode MTP

2025-09-26 14:16:23 +08:00

..

sched

[Feature] support clear data (#4185)

2025-09-21 20:41:27 +08:00

__init__.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

args_utils.py

remove debug code

2025-09-25 20:58:08 +08:00

common_engine.py

[BugFix] fix clear data (#4227)

2025-09-24 11:23:44 +08:00

engine.py

supports internode_ll_two_stage (#4143)

2025-09-22 14:55:06 +08:00

expert_service.py

add w4afp8 offline script (#3636)

2025-08-29 17:56:05 +08:00

kv_cache_interface.py

polish code with new pre-commit rule (#2923)

2025-07-19 23:19:27 +08:00

request.py

feat: add draft_logprobs for Speculative Decode MTP

2025-09-26 14:16:23 +08:00

resource_manager.py

[feat] add metrics for yiyan adapter (#3219) (#3614)

2025-08-30 23:20:58 +08:00

sampling_params.py

[Feature] bad words support v1 scheduler and specifiy token ids (#3608)

2025-08-25 20:14:51 -07:00