mirror of
https://github.com/NVIDIA/TensorRT-LLM.git
synced 2026-02-06 03:01:50 +08:00
13 lines
273 B
YAML
13 lines
273 B
YAML
# Please replace `ctx_hostname` and `gen_hostname` with the actual addresses.
|
|
hostname: localhost
|
|
port: 8000
|
|
backend: pytorch
|
|
context_servers:
|
|
num_instances: 1
|
|
urls:
|
|
- "ctx_hostname:8001"
|
|
generation_servers:
|
|
num_instances: 1
|
|
urls:
|
|
- "gen_hostname:8002"
|