Call for Proposals
Buy Tickets
Buy Tickets
中文 English
Call for Proposals
Buy Tickets
Previous Running Millions of Agents at Tencent: CubeSandbox as the Hands Behind the Harness Brain
All Schedule
Next From Rollout to Weight Synchronization: How Mooncake Supports High-Performance RL and Inference
Agentic AI Infrastructure Forum

vLLM and Ascend: Plugin-Based Architecture and MoE Expert Load Balancing in Practice

Date 2026-10-16 Time 14:35-15:10 Location 2F – KAI XUAN 2

Talk overview

Abstract to be announced.

Speakers

Frey Tian
Frey Tian Huawei Ascend Computing Inference Technology Expert, Huawei