A programmable Mixture-of-Models router for heterogeneous LLM inference
Implementation of Switch Transformers from the paper: "Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity"
LLM Semantic Router: Intelligent Mixture-of-Models (MoM) System with Privacy Preservation and Prompt Guard. The semantic router intelligently directs OpenAI compliant API requests to the most suitable backend models based on semantic understanding of request content.
GPS for your LLMs
The implementation of mixtures for different tasks.
Identify and protect personal data in text by intercepting and masking PII using Java middleware for enhanced data privacy compliance.
OpenAI-compatible API that routes each request through a multi-model proposer/refuter/synthesizer pipeline. FastAPI, native tool calling, pluggable OpenRouter and mock upstreams.
MC-1 — Mixture-of-Models Intelligence by ColomboAI
Add a description, image, and links to the mixture-of-models topic page so that developers can more easily learn about it.
To associate your repository with the mixture-of-models topic, visit your repo's landing page and select "manage topics."