NeurIPS 2026: Ascend RL Training System Hits 222% Speedup with Adaptive Scheduling
The Shenzhen Institute of Big Data and Huawei present ASP, an adaptive scheduling pipeline for multi-instance asynchronous RL training on Ascend 910B3 NPUs, eliminating padding, skewness, and sorting bubbles to achieve 222% higher generation throughput and 76% lower iteration time, validated at NeurIPS 2026 and deployed in telecom cutting training from three months to two.
