Skills and MCP tagged “vllm”

google-cloud-solution-guided-gke-ai-migration official google skill Guides existing AI inference workloads from Cloud Run, Gemini API, or another environment to self-hosted inference on GKE. Claude Code Gemini CLI CX Codex 4,700installs quantized-export Seth Hobson skill Exports promoted checkpoints and LoRA adapters as FP8, AWQ, GGUF, or merged safetensors. Use it before deploying a model. Claude Code CX Codex Cursor 2,600installs grpo-rlvr-training Seth Hobson skill Configures GRPO and RLVR training pipelines for tasks with verifiable outcomes. Useful when evaluating models with code execution, unit tests, or strict schemas. Claude Code CX Codex Cursor 2,600installs llm-architect VoltAgent Community subagent Designs production LLM architectures: covers RAG, LoRA fine-tuning, inference serving with vLLM, and multi-model routing. Essential when managing token budgets and latency targets. Claude Code 649installs