TokenRouter: Efficient Serving System for Token-Level LLM Routing
Paper • 2610.12242 • Published • 87
blouce shan
blouce
AI & ML interests
None yet
Recent Activity
upvoted a paper about 7 hours ago
TokenRouter: Efficient Serving System for Token-Level LLM Routing upvoted a paper 10 days ago
Improving Test-Time Scaling with Adaptive Looped Transformers upvoted a paper 11 months ago
Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language ModelsOrganizations
None yet