At MWC Shanghai 2026, China Mobile Hubei and Huawei announced the live-network validation of Huawei's AI Inference Acceleration Solution. Powered by Huawei's OceanStor A800 storage, Ascend A3 SuperPoD, and Unified Cache Manager (UCM), the service is designed to deliver up to a 372 percent improvement in token throughput for long-sequence AI inference workloads.