InferX — Serverless GPU Inference Platform for Production Workloads

Tenant Namespace Pod Name State Node Name Req. GPU Count Req. GPU vRam (MB) Type Standby (MB) Allocated GPU vRam (MB) Allocated GPU Slots
GPU Pageable Pinned GPU Slot Count
public Qwen public/Qwen/IntelliAsk-Qwen3-32B-450-Merged/76/252 Standby computeinstance-e00r2jrqynf83a8b4f 2 58000 Restore Mem : 115824 File : 3648 File : 4 0 N/A