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.

By orchestra-research · 857 installs

npx skills add orchestra-research/ai-research-skills --skill serving-llms-vllm

Source repository · Upstream listing