Keynote: Running Large Models on Diverse AI Chips: PyTorch + Open-Source Stack (FlagO...
summary
Discusses running large models across different AI chips using PyTorch together with an open-source stack called FlagOS. Covers architecture-free deployment techniques enabled by FlagOS to make models portable across hardware.
AI-written summary · about
related talks
01h 07m📚 Building Portable Large Models on Heterogeneous AI Accelerators Wit...
12mKeynote: AI Infrastructure
16mKeynote: An Open-Source Stack for AI Compute: Kubernetes + Ray + PyTorch + vLLM
06mKeynote: Intel and PyTorch: Enabling AI Everywhere with Ubiquitous Hardware and Open...
11mKeynote: Open Source Stack Empowers the AI Era
06mKeynote: PyTorch Lightning: Powering the GenAI Revolution from Research to the...
24mKeynote: Next-generation frameworks for Large-scale AI
16mKeynote: Marin: An Open Lab for Frontier AI
