Discrepancy in LayerNorm Calculations?August 20, 2024 · 4 min readZ. YuanDosaid maintainer, Full-Stack AI EngineerCurious about the numbers? Let's calculate and compare.
The PyTorch List TrapFebruary 20, 2024 · 2 min readZ. YuanDosaid maintainer, Full-Stack AI EngineerDiscovering and solving PyTorch OOM issues.