Engineering
BAGEL 复现
ByteDance's BAGEL model uses a Mixture-of-Transformer-Experts architecture for unified image understanding, generation, and editing, requiring Ampere GPUs for full bfloat16 support.
Software engineering insights and best practices
ByteDance's BAGEL model uses a Mixture-of-Transformer-Experts architecture for unified image understanding, generation, and editing, requiring Ampere GPUs for full bfloat16 support.
A technical guide for reproducing the VILA-U multimodal model on AutoDL, covering environment setup, storage optimization, model download, inference, and common troubleshooting.
A developer documents the process of reproducing BundleFusion on Ubuntu, detailing compilation fixes, GPU configuration, RealSense integration, and data feeding challenges.