TokenRouter: Efficient Serving System for Token-Level LLM Routing
AI & ML interests
None defined yet.
Recent Activity
View all activity
Papers
SALAD: Achieve High-Sparsity Attention via Efficient Linear Attention Tuning for Video Diffusion Transformer
Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models
models 19
nics-efc/VPR-Qwen3-4B-Minesweeper
Text Generation • 4B • Updated • 195
nics-efc/VPR-Qwen3-4B-Base-Math-Mixed
Text Generation • 4B • Updated • 215
nics-efc/VPR-Qwen3-4B-Sudoku
Text Generation • 4B • Updated • 288 • 1
nics-efc/VPR-Qwen3-4B-Sokoban
Text Generation • 4B • Updated • 391 • 1
nics-efc/C2C_Fuser
Text Generation • Updated • 6
nics-efc/Standard-0.6B
0.6B • Updated • 49
nics-efc/TaH-plus-0.6B
0.6B • Updated • 52
nics-efc/CoLLM_Qwen3_0_6B
0.8B • Updated • 4
nics-efc/CITER_Qwen3_0_6B_Qwen3_32B
Updated
nics-efc/MARSHAL-Mini-Hanabi-Qwen3-4B
Text Generation • 4B • Updated • 17
datasets 10
nics-efc/TaH-openr1-math-75k
Updated • 28
nics-efc/R2R_Router_Training_Qwen3-0.6B_Qwen3-30B-A3B
Viewer • Updated • 9.3M • 19
nics-efc/R2R_Router_Training_Qwen3-4B_Qwen3-32B
Viewer • Updated • 18.3M • 27
nics-efc/R2R_Router_Training_Qwen3-1.7B_Qwen3-8B
Viewer • Updated • 21.9M • 56
nics-efc/R2R_Router_Training_Qwen3-0.6B_Qwen3-8B
Viewer • Updated • 22.2M • 27
nics-efc/TaH-openr1-mixture-100k
Updated • 79
nics-efc/R2R_query
Viewer • Updated • 2.93k • 60
nics-efc/R2R_Router_Training
Viewer • Updated • 8.19M • 224 • 4
nics-efc/MoA_Long_HumanQA
Viewer • Updated • 3.5k • 50 • 4
nics-efc/MoA_Long_Retrieval
Viewer • Updated • 4.4k • 20 • 4