24 lines
615 B
Plaintext
24 lines
615 B
Plaintext
[supervisord]
|
|
nodaemon=true
|
|
logfile=/dev/stdout
|
|
logfile_maxbytes=0
|
|
loglevel=info
|
|
|
|
[program:vllm]
|
|
command=python3 -m vllm.entrypoints.openai.api_server --model /root/.cradle/Alibaba/Qwen3-4B --served-model-name Qwen3-4B --tensor-parallel-size 2 --port 30000 --api-key token-abc123
|
|
autostart=true
|
|
autorestart=true
|
|
stdout_logfile=/dev/stdout
|
|
stdout_logfile_maxbytes=0
|
|
stderr_logfile=/dev/stderr
|
|
stderr_logfile_maxbytes=0
|
|
|
|
[program:ui]
|
|
command=python3 /app/meta_ui.py --port 30001
|
|
autostart=true
|
|
autorestart=true
|
|
stdout_logfile=/dev/stdout
|
|
stdout_logfile_maxbytes=0
|
|
stderr_logfile=/dev/stderr
|
|
stderr_logfile_maxbytes=0
|