yanghou2000

Error in loading checkpoint

2

# Background Linux x86 timesfm cpu version use slurm to submit job. already ensure that conda env is activated after using SBATCH and before running python code # Code that...

According to this pytorch [quantization guide](https://pytorch.org/blog/int8-quantization/), pytorch now supports a faster backend for int8 called **X86** as a replace for **FBGEMM**. I find that in the tch-rs [jit-quantized example](https://github.com/LaurentMazare/tch-rs/blob/a90854b2135b91546ca6082418d478126e1f6a26/examples/jit-quantized/main.rs) tch-rs...