nano-vllm is a minimal, educational, and performant LLM inference engine that reimplements core vLLM concepts in clean Python for easy understanding and extension.
nano-vllm — Lightweight LLM Serving Engine
nano-vllm is a minimal, educational, and performant LLM inference engine that reimplements core vLLM concepts in clean Python for easy understanding and extension.
Installation avec revue préalable
Cet actif nécessite une revue. Le prompt copié demande un dry-run, affiche les écritures, puis continue seulement après confirmation.
npx -y tokrepo@latest install 27f1bbc3-470d-11f1-9bc6-00163e2b0d79 --target codexDry-run d'abord, confirmez les écritures, puis lancez cette commande.
Fil de discussion
Actifs similaires
Cadence — Distributed Workflow Execution Engine by Uber
Cadence is a distributed, scalable, fault-tolerant workflow orchestration engine developed by Uber for executing long-running business logic as durable, stateful workflows that survive process and infrastructure failures.
Babylon.js — Powerful 3D Game and Rendering Engine
Babylon.js is a powerful, beautiful, simple, open 3D game and rendering engine for the web. WebGL + WebGPU, Playground IDE, Node Material Editor, GUI system, physics, and VR/AR support. Microsoft-backed with enterprise polish.
Unsloth — 2x Faster Local LLM Training & Inference
Unsloth is a unified local interface for running and training AI models. 58.7K+ GitHub stars. 2x faster training with 70% less VRAM across 500+ models including Qwen, DeepSeek, Llama, Gemma. Web UI wi
pywebview — Lightweight Python GUI with Web Technologies
A cross-platform Python library that creates native GUI windows with embedded web views, letting you build desktop applications using HTML, CSS, and JavaScript for the frontend with Python for the backend.