Janus: Multi-LLM Serving at Production Scale

Production LLM serving multiplexes hundreds of heterogeneous models on shared clusters, exposing three challenges that existing systems fail to address simultaneously: unpredictable bursts, power-law application popularity, and heterogeneous yet complementary resource demands. We present Janus, a Service-Engine co-designed multi-model serving system built around dual-timescale scheduling. At the Service layer, a Model Scheduler driven by a Performance Oracle combines vector bin-packing every 30 seconds for steady-state colocation with elastic scaling every 0.5 seconds. A new LST-IMH Request Scheduler maximizes SLO attainment with a proven 2-approximation guarantee. At the Engine layer, xTensor virtualizes HBM, while a three-state model lifecycle and device-to-device (D2D) fork enable elastic multi-model colocation and sub-second burst scale-out. We deploy Janus on a 768-device production cluster serving 62 applications and 45.6 M requests/day, and evaluate it with a 603 K-request open-loop replay sampled from that production day. Janus maintains 0.97-1.0 SLO attainment, versus 0.80-0.92 for the strongest baseline, while using 13,440 device-hours/day, 27% less than static Serverless-LLM. Janus is available as open source at https://github.com/Janus2026/Janus.