23 lines
657 B
Python
Executable File
23 lines
657 B
Python
Executable File
import multiprocessing
|
||
import os
|
||
|
||
# 基础配置
|
||
bind = "0.0.0.0:80"
|
||
worker_class = "uvicorn.workers.UvicornWorker"
|
||
loglevel = "info"
|
||
accesslog = "-"
|
||
errorlog = "-"
|
||
|
||
# 关键生产参数
|
||
workers = 2 # 先用 2 个（ML 场景推荐 1~4，根据 CPU 核数和内存调整）
|
||
timeout = 300 # 5 分钟，足够模型加载和慢推理
|
||
graceful_timeout = 300
|
||
preload_app = True # ★★★ 必须加！模型只加载一次，内存大幅节省
|
||
|
||
# 防止内存泄漏（ML 服务常见问题）
|
||
max_requests = 1000
|
||
max_requests_jitter = 100
|
||
|
||
# 其他优化
|
||
keepalive = 5
|
||
worker_connections = 1000 |