模型推理全异步化改造: - 计算节点 InferenceSession 改为后台线程异步加载模型,load 立即返回, 加载期间事件循环保持响应(/inference/status 与 /health 不阻塞) - 后端模型加载改为异步派发 + 轮询对账器(reconcile_inference_loads), 任务状态由 starting 自动推进到 ready/error,解决多节点启动超时 (timeout of 120000ms exceeded) - 推理删除/卸载改为任务感知 + 短超时,删除先删记录再 best-effort 卸载, 不再被不可达节点阻塞;同节点新模型替换旧任务标记失效 - 流式对话透传 task_id/node_id 路由到真正加载模型的算力节点, useStreamChat 解析 SSE 错误帧以干净文案展示 - 对话历史按任务 id 本地持久化,退出重进可恢复;移除页脚提示文本 - 新增后端推理异步加载与计算节点异步状态机单元测试 Co-Authored-By: Claude <noreply@anthropic.com>
42 lines
1.0 KiB
Plaintext
42 lines
1.0 KiB
Plaintext
server {
|
|
listen 80;
|
|
server_name _;
|
|
|
|
root /usr/share/nginx/html;
|
|
index index.html;
|
|
|
|
client_max_body_size 200m;
|
|
|
|
location ^~ /modelTF/ {
|
|
proxy_pass ${BACKEND_PROXY_PASS};
|
|
proxy_http_version 1.1;
|
|
proxy_set_header Host $host;
|
|
proxy_set_header X-Real-IP $remote_addr;
|
|
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
|
proxy_set_header X-Forwarded-Proto $scheme;
|
|
proxy_read_timeout 900s;
|
|
proxy_send_timeout 900s;
|
|
}
|
|
|
|
location = /modelTF {
|
|
proxy_pass ${BACKEND_PROXY_PASS};
|
|
proxy_http_version 1.1;
|
|
proxy_set_header Host $host;
|
|
proxy_set_header X-Real-IP $remote_addr;
|
|
proxy_set_header X-Forwarded-For $proxy_add_x_forwarded_for;
|
|
proxy_set_header X-Forwarded-Proto $scheme;
|
|
proxy_read_timeout 900s;
|
|
proxy_send_timeout 900s;
|
|
}
|
|
|
|
location ~* \.(?:js|css|png|jpg|jpeg|gif|ico|svg|woff|woff2|ttf)$ {
|
|
try_files $uri =404;
|
|
expires 30d;
|
|
add_header Cache-Control "public, immutable";
|
|
}
|
|
|
|
location / {
|
|
try_files $uri $uri/ /index.html;
|
|
}
|
|
}
|