Sglang简明部署教程-Qwen3
运维部署交流
1
帖子
1
发布者
33
浏览
1
关注中
-
前提条件
- 请确保你已经安装好Nvidia驱动
- 是Linux服务器
- 安装好了Docker
- Debian12系统
- 良好的国际化网络环境
参考:
Nvidia vGPU 18.0以上 GRID或CloudGame驱动Patch许可教程
Tesla T10 PVE 服务器配置指南安装NVIDIA 容器运行时
curl -fsSL https://nvidia.github.io/libnvidia-container/gpgkey | sudo gpg --dearmor -o /usr/share/keyrings/nvidia-container-toolkit-keyring.gpg \ && curl -s -L https://nvidia.github.io/libnvidia-container/stable/deb/nvidia-container-toolkit.list | \ sed 's#deb https://#deb [signed-by=/usr/share/keyrings/nvidia-container-toolkit-keyring.gpg] https://#g' | \ sudo tee /etc/apt/sources.list.d/nvidia-container-toolkit.list
sudo apt-get update
export NVIDIA_CONTAINER_TOOLKIT_VERSION=1.17.8-1 sudo apt-get install -y \ nvidia-container-toolkit=${NVIDIA_CONTAINER_TOOLKIT_VERSION} \ nvidia-container-toolkit-base=${NVIDIA_CONTAINER_TOOLKIT_VERSION} \ libnvidia-container-tools=${NVIDIA_CONTAINER_TOOLKIT_VERSION} \ libnvidia-container1=${NVIDIA_CONTAINER_TOOLKIT_VERSION}
sudo nvidia-ctk runtime configure --runtime=docker
sudo systemctl restart docker
配置docker compose(需要自行配置相关内容)
services: sglang: image: lmsysorg/sglang:latest container_name: sglang volumes: #- /home/fushinn/sglang/cache/huggingface:/root/.cache/huggingface # If you use modelscope, you need mount this directory - ${HOME}/.cache/modelscope:/root/.cache/modelscope - ./jinja:/root/jinja restart: always network_mode: host # required by RDMA privileged: true # required by RDMA # Or you can only publish port 30000 # ports: # - 30000:30000 environment: HF_TOKEN: "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" # if you use modelscope to download model, you need set this environment SGLANG_USE_MODELSCOPE: true entrypoint: python3 -m sglang.launch_server command: --model-path Qwen/Qwen3-4B --host 127.0.0.1 --port 30000 --tool-call-parser qwen25 --reasoning-parser qwen3 #--chat-template /root/jinja/qwen3_nonthinking.jinja ulimits: memlock: -1 stack: 67108864 ipc: host healthcheck: test: ["CMD-SHELL", "curl -f http://localhost:30000/health || exit 1"] deploy: resources: reservations: devices: - driver: nvidia device_ids: ["0"] capabilities: [gpu]
配置jinja(可选内容)
{%- if tools %} {{- '<|im_start|>system\n' }} {%- if messages[0].role == 'system' %} {{- messages[0].content + '\n\n' }} {%- endif %} {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }} {%- for tool in tools %} {{- "\n" }} {{- tool | tojson }} {%- endfor %} {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }} {%- else %} {%- if messages[0].role == 'system' %} {{- '<|im_start|>system\n' + messages[0].content + '<|im_end|>\n' }} {%- endif %} {%- endif %} {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %} {%- for message in messages[::-1] %} {%- set index = (messages|length - 1) - loop.index0 %} {%- if ns.multi_step_tool and message.role == "user" and message.content is string and not(message.content.startswith('<tool_response>') and message.content.endswith('</tool_response>')) %} {%- set ns.multi_step_tool = false %} {%- set ns.last_query_index = index %} {%- endif %} {%- endfor %} {%- for message in messages %} {%- if message.content is string %} {%- set content = message.content %} {%- else %} {%- set content = '' %} {%- endif %} {%- if (message.role == "user") or (message.role == "system" and not loop.first) %} {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }} {%- elif message.role == "assistant" %} {%- set reasoning_content = '' %} {%- if message.reasoning_content is string %} {%- set reasoning_content = message.reasoning_content %} {%- else %} {%- if '</think>' in content %} {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %} {%- set content = content.split('</think>')[-1].lstrip('\n') %} {%- endif %} {%- endif %} {%- if loop.index0 > ns.last_query_index %} {%- if loop.last or (not loop.last and reasoning_content) %} {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }} {%- else %} {{- '<|im_start|>' + message.role + '\n' + content }} {%- endif %} {%- else %} {{- '<|im_start|>' + message.role + '\n' + content }} {%- endif %} {%- if message.tool_calls %} {%- for tool_call in message.tool_calls %} {%- if (loop.first and content) or (not loop.first) %} {{- '\n' }} {%- endif %} {%- if tool_call.function %} {%- set tool_call = tool_call.function %} {%- endif %} {{- '<tool_call>\n{"name": "' }} {{- tool_call.name }} {{- '", "arguments": ' }} {%- if tool_call.arguments is string %} {{- tool_call.arguments }} {%- else %} {{- tool_call.arguments | tojson }} {%- endif %} {{- '}\n</tool_call>' }} {%- endfor %} {%- endif %} {{- '<|im_end|>\n' }} {%- elif message.role == "tool" %} {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} {{- '<|im_start|>user' }} {%- endif %} {{- '\n<tool_response>\n' }} {{- content }} {{- '\n</tool_response>' }} {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %} {{- '<|im_end|>\n' }} {%- endif %} {%- endif %} {%- endfor %} {%- if add_generation_prompt %} {{- '<|im_start|>assistant\n<think>\n\n</think>\n\n' }} {%- endif %}
启动Compose
docker compose up -d
测试
curl http://127.0.0.1:30000/v1