3 boosters for "inference" — AI-graded, open source, ready to install
A skill for adapting and optimizing Hugging Face or custom LLM models to run efficiently on vLLM with Ascend NPU support, enabling developers to validate and deploy models with deterministic testing and single-commit delivery.
BlockRun MCP Server enables Claude users to access 30+ AI models through x402 micropayments without requiring API keys. This benefits developers who want flexible model access and cost-efficient AI inference across multiple providers.
A physics-focused MCP server that orchestrates computational tools (CAS, plotting, natural language inference) to help physicists and students solve complex equations, visualize results, and understand physics concepts. Ideal for educators, researchers, and learners working with quantum mechanics and classical physics problems.
