2 Commits (5017cc6e0e500c2686b9f18819257feac1a0bf18)

Author	SHA1	Message	Date
alexhegit	6d895f8b25	Do the device_map more automaticlly for multi-GPUs ... The accelerate lib provide some functions to do the device_map automaticlly. This patch use infer_auto_device_map() to relpace the hard codes which splite the mode by hand. It works well with my two GPUs(6GB-RTX3060 + 12GB-RTX3060). Signed-off-by: Alex He <heye_dev@163.com>	2023-08-18 00:08:24 +08:00
Qin Jianxiang	08ffab941f	Multiple GPUs support: migrate the code from ChatGLM-6B, make a few modifications to support ChatGLM2.	2023-06-26 10:29:19 +08:00