RYDE-WORK/Langchain-Chatchat
1
0
Fork 0
mirror of https://github.com/RYDE-WORK/Langchain-Chatchat.git synced 2026-02-06 14:57:44 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

更新多卡部署

Browse Source
This commit is contained in:
hzg0601 2023-08-14 11:24:52 +08:00
parent 84e4981cc1
commit 6590ca32db
2 changed files with 2 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
server/llm_api.py
View File

@ -44,7 +44,7 @@ def create_model_worker_app(
gptq_act_order=None, gptq_act_order=None,
gpus=None, gpus=None,
num_gpus=1, num_gpus=1,
max_gpu_memory=None, max_gpu_memory="20GiB",
cpu_offloading=None, cpu_offloading=None,
worker_address=base_url.format(model_worker_port), worker_address=base_url.format(model_worker_port),
controller_address=base_url.format(controller_port), controller_address=base_url.format(controller_port),

1
server/llm_api_launch.py
View File

@ -76,6 +76,7 @@ parser.add_argument("--num-gpus", type=int, default=1)
parser.add_argument( parser.add_argument(
"--max-gpu-memory", "--max-gpu-memory",
type=str, type=str,
default="20GiB",
help="The maximum memory per gpu. Use a string like '13Gib'", help="The maximum memory per gpu. Use a string like '13Gib'",
) )
parser.add_argument( parser.add_argument(