Penck
Results
3
comments of
Penck
 onnx: 1.15.0, onnxruntime: 1.17.1 > more logs, more details
> more logs, more details it's config.yaml problem, should write tokens into config.yaml
> Ascend NPUs are Huawei's neural network chips. Does AutoGPTQ currently support inference/training on Ascend NPUs? Do you have any other solutions on Ascend NPU？