3 Commits

Author	SHA1	Message	Date
chenbin11200	ff948d5403	feat(nn4k): not load model to cuda when using deepspeed (#207)	2024-04-19 11:20:25 +08:00
chenbin11200	bf57b3319f	feat(nn4k): support huggingface decode only model local inference (#128) ... Co-authored-by: xionghuaidong <huaidong.xhd@antgroup.com>	2024-03-08 13:54:15 +08:00
xionghuaidong	945cf8fbbd	feat(nn4k): implement text embeddings (#104)	2024-02-02 16:29:24 +08:00