“backend support”

guidance

A guidance language for controlling large language models.

keras

Deep Learning for humans

vllm-mlx

OpenAI and Anthropic compatible server for Apple Silicon. Run LLMs and vision-language models (Llama, Qwen-VL, LLaVA) with continuous batching, MCP tool calling, and multimodal support. Native MLX bac

vllm

A high-throughput and memory-efficient inference and serving engine for LLMs

nocobase

An open-source AI + no-code platform for rapid business system development

verl

A Flexible and Efficient RL Post-Training Framework