Logging the memory, it seems like it starts the forward pass, memory starts increasing on GPU 0, then OOMs. I wonder if it’s trying to be smart and planning ahead and dequantizing multiple layers at a time. Dequantizing each layer uses ~36 GB of memory so if it was doing this that could cause it to use too much memory. Maybe if we put each layer on alternating GPU’s it could help.
二、找不到剧，也数不齐5亿播放量
。新收录的资料对此有专业解读
A young person is considered Neet if they are unemployed (looking for work) or economically inactive (not actively looking for work and not waiting to start a job or caring for family).
Pushing and Pulling: Three reactivity algorithms (8th March 2026) on Hacker News