Ben Rood
Ben Rood
> [@hsb1995](https://github.com/hsb1995) > > 1. The link you referred to is a GPTQ quant model made by AutoRound. However, that model has not been benchmarked, that i am aware of...
期待,目前的速度有点慢,3060的onnx推理似乎RTF在0.4~0.7左右
OOM occurs to me with new 580 driver with 4090 48G. The driver file is NVIDIA-Linux-x86_64-580.95.05.run. I've try all other method, nothing works. Then I down-grade driver to NVIDIA-Linux-x86_64-570.195.03.run, everything...