Vela 3.0 Router from vLLM, KR Labs and AMD
Merging routing and span extraction into one call cuts the latency and plumbing usually needed to split prompts across pipeline stages. Teams building semantic routers or traffic-classification layers on small open models can now pick a size from 0.3B upward to match their hardware budget. The AMD involvement also signals the router is tuned beyond NVIDIA-only deployments.
The vLLM Semantic Router team, KR Labs and AMD released Vela 3.0. The update combines routing decisions and span extraction into a single call. It ships with six open models ranging from 0.3B to 27B parameters. The smaller sizes give deployers more flexibility in how lightweight the router can run.
Great work from the vLLM Semantic Router, KR Labs, and @AMD teams on Vela 3.0! Routing decisions and span extraction in one call, with six open models from 0.3B to 27B. More flexibility in what the router can detect and how small it can run.
