Content on this site is AI-generated and may contain errors. If you find issues, please report at GitHub Issues .

LLM Model Routing: Intelligent Model Selection and Hybrid Inference

Automatically select the right LLM based on task complexity. Covers the full spectrum from simple classifiers to RL-based online learning, query-level to token-level routing, and single-model selection to multi-model collaboration.

  1. 1

    Model Routing Landscape: Why One Model Isn't Enough

    Advanced
    #model-routing#llm#cost-optimization#system-design
  2. 2

    Routing Classifiers: Letting Small Models Decide Who Answers

    Advanced
    #model-routing#classifier#matrix-factorization#bert#semantic-routing
  3. 3

    RouteLLM in Practice: From Preference Data to Production Routing

    Advanced
    #model-routing#routellm#matrix-factorization#training#deployment
  4. 4

    Factorization Machines and LLM Routing: From FM Theory to MF Router

    Advanced
    #model-routing#factorization-machines#matrix-factorization#routellm
  5. 5

    Cascade and Self-Verification: Try the Cheap Model First, Upgrade If Needed

    Advanced
    #model-routing#cascade#self-verification#pomdp#frugalgpt#automix
  6. 6

    Hybrid LLM: Intelligent Routing Between Local and Cloud

    Advanced
    #model-routing#hybrid-llm#local-cloud#privacy#latency
  7. 7

    Online Learning and Cost Optimization: Routers Need to Evolve Too

    Advanced
    #model-routing#bandit#reinforcement-learning#pareto#cost-optimization
  8. 8

    Multi-Model Collaboration: From Picking One to Using Many

    Advanced
    #model-routing#mixture-of-agents#ensemble#council-mode#collaboration