9 Commits

Author	SHA1	Message	Date
Yuan Xiaolan	25aa2d94aa	cp dynamic Cfp8 (#4120) ... * supports dynamic Cfp8 * add unittest * fix dynamic Cfp8 computing error * fix Cfp8 for RL load --------- Co-authored-by: carryyu <569782149@qq.com>	2025-09-17 11:55:47 +08:00
freeliuzc	2f473ba966	[Feature][MTP]Support MTP for rl-model (#4009) ... * qk norm for speculate decode C16 * support mtp in v1_scheduler mode * support mtp rope_3d * support mtp features * add unit test && del some log --------- Co-authored-by: yuanxiaolan <yuanxiaolan01@baidu.com> Co-authored-by: xiaoxiaohehe001 <hiteezsf@163.com>	2025-09-10 13:34:37 +08:00
Liumengyuan	e93d4cfcdd	Add with_output version AppendAttention (#3302) ... * get use_output from fd_config * add clear TODO description * add mask_offset para to align with develop * fix bug * fix use_output logic * fix sot bug	2025-08-28 17:10:18 +08:00
lzy	1e06b9fa6d	make append_attn supports mask_offset (#3138) ... * make append_attn supports mask_offset * add unittest	2025-08-14 03:40:55 -07:00
Ryan	ed6bff215a	fix custom op order rms_norm_eps (#3348)	2025-08-13 10:12:49 +08:00
Yuan Xiaolan	7ce00e597c	support qk norm (#3145)	2025-08-05 16:46:14 +08:00
周周周	ddb10ac509	[Inference, rename] remove padding_offsets from atten use batch_id_per_token (#2880) ... * remove padding_offsets from atten	2025-07-17 18:41:31 +08:00
周周周	aa76085d1f	[Attention] remove cum_offsets from atten, and use cu_seqlens_q (#2870) ... [Attention] remove cum_offsets from atten, and use cu_seqlens_q (#2870)	2025-07-16 20:10:57 +08:00
jiangjiajun	684703fd72	[LLM] First commit the llm deployment code	2025-06-09 19:20:15 +08:00