vLLM Semantic Router: Signal Driven Decision Routing for Mixture-of-Modality Models
Open paper
Benchmark
Model
Rank
Results
visual-question-answering-vqa-on-blink
d3
#27
Accuracy: 59.9
visual-question-answering-vqa-on-realworldqa
d3
#32
Accuracy: 73.4
Rank counts only results with a code link.