How We Scaled Kimi K2.5: Training Secrets of a 1 Trillion Parameter Model | GTC 2026 Keynote
Open Academy
"How is a 1-Trillion Parameter Model Trained?" Discover Kimi K2.5's scaling strategy, directly revealed by Moonshot AI on stage at GTC 2026, now available in Korean on Inflearn. 2x Token Efficiency · 1 Million Token Context · 1,000 Agent Swarm The next step for open-source LLMs is here. * This course is released for free through an official collaboration between Moonshot AI, the creators of Kimi, and Inflearn.
초급
LLM, AI Agent




