serving-llms-vllm
Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism.
来源信息
- 仓库
- synthetic-sciences/openscience
- 最近来源活动
- 2026年9月16日 06:26
- 检测到的 SKILL.md 语言
- 英语
- 星标
- 4,370
- Forks
- 550
安装方式
默认使用会先检查来源的 Prompt;你也可以切换为直接命令,或下载本地副本。
检查来源文件
决定是否安装前,请先阅读 SKILL.md,以及 SkillsMP 当前展示的配套文件。
正在显示 SKILL.md
| name | serving-llms-vllm |
|---|---|
| description | Serves LLMs with high throughput using vLLM's PagedAttention and continuous batching. Use when deploying production LLM APIs, optimizing inference latency/throughput, or serving models with limited GPU memory. Supports OpenAI-compatible endpoints, quantization (GPTQ/AWQ/FP8), and tensor parallelism. |