文档(金鹏): 2026-08-06 章节 48 篇文章摘要归档
- 46 篇原文+摘要双文件归档(按 来源/作者 分层,复用本地归档 20 篇+新抓取 26 篇) - 即梦生成 9 组主题配图(大图+列表缩略图)存入 知识/金鹏/20260806/ - 章节重组为 9 个主题分组并挂接摘要引用
This commit is contained in:
@@ -0,0 +1,56 @@
|
||||
# Welcome to NVIDIA Dynamo
|
||||
|
||||
> **来源**:NVIDIA Dynamo 文档
|
||||
> **作者**:未知
|
||||
> **发布日期**:2026-08-06
|
||||
> **原文链接**:https://docs.nvidia.com/dynamo/latest/index.html
|
||||
|
||||
---
|
||||
|
||||
NVIDIA Dynamo Platform 是一个高性能、低延迟的推理框架,旨在服务于所有 AI 模型——支持任何框架、任何架构、任何部署规模。
|
||||
|
||||
> 本指南是某一特定时间点的快照。获取最新信息和示例,请参见 Dynamo GitHub 仓库。
|
||||
|
||||
## Quickstart(快速开始)
|
||||
|
||||
只需几个命令即可在本地开始使用 Dynamo:
|
||||
|
||||
**1. 安装 Dynamo**
|
||||
|
||||
```
|
||||
# Install uv (recommended Python package manager)
|
||||
curl -LsSf https://astral.sh/uv/install.sh | sh
|
||||
|
||||
# Create virtual environment and install Dynamo
|
||||
uv venv venv
|
||||
source venv/bin/activate
|
||||
uv pip install "ai-dynamo[sglang]==0.4.1" # or [vllm], [trtllm]
|
||||
```
|
||||
|
||||
**2. 启动 etcd/NATS**
|
||||
|
||||
```
|
||||
# Fetch and start etcd and NATS using Docker Compose
|
||||
curl -fsSL -o docker-compose.yml https://raw.githubusercontent.com/ai-dynamo/dynamo/release/0.4.1/deploy/docker-compose.yml
|
||||
docker compose -f docker-compose.yml up -d
|
||||
```
|
||||
|
||||
**3. 运行 Dynamo**
|
||||
|
||||
```
|
||||
# Start the OpenAI compatible frontend (default port is 8080)
|
||||
python -m dynamo.frontend
|
||||
|
||||
# In another terminal, start an SGLang worker
|
||||
python -m dynamo.sglang --model-path Qwen/Qwen3-0.6B
|
||||
```
|
||||
|
||||
**4. 测试部署**
|
||||
|
||||
```
|
||||
curl localhost:8080/v1/chat/completions \
|
||||
-H "Content-Type: application/json" \
|
||||
-d '{"model": "Qwen/Qwen3-0.6B",
|
||||
"messages": [{"role": "user", "content": "Hello!"}],
|
||||
"max_tokens": 50}'
|
||||
```
|
||||
Reference in New Issue
Block a user