Vllm

Deploy and tune vLLM OpenAI-compatible servers: PagedAttention KV budgeting, continuous batching, chunked prefill, tensor parallel, quantization, and preemption/OOM failure modes.

alivirgo Updated 3 repo stars

File contents

alivirgo/major-ai-skills commit c2a4f0ba52

Frequently asked questions

npx get-skill add alivirgo/vllm