[wrapq] torch.bfloat16 induces torch internal error

[dayo09]

What?

(AFAIK) Some huggingface models are distributed in torch.bfloat16 format without dtype manifested.
While trying examples of Llama and Qwen, I faced this error.

  File "/home/dayo/miniconda3/envs/py310-tvm/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1776, in _wrapped_call_impl
    return self._call_impl(*args, **kwargs)
  File "/home/dayo/miniconda3/envs/py310-tvm/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1787, in _call_impl
    return forward_call(*args, **kwargs)
  File "/home/dayo/git/TICO/tico/quantization/wrapq/wrappers/nn/quant_linear.py", line 57, in forward
    w = self.obs_weight.fake_quant(w)
  File "/home/dayo/git/TICO/tico/quantization/wrapq/observers/affine_base.py", line 152, in fake_quant
    return torch.fake_quantize_per_channel_affine(
RuntimeError: !needs_dynamic_casting<func_t>::check(iter) INTERNAL ASSERT FAILED at "/pytorch/aten/src/ATen/native/cpu/Loops.h":311, please report a bug to PyTorch. 

After changing dtypes for model/inputs into torch.float32, it passed.

/cc @mhs4670go

From this example #485 (comment)

[mhs4670go]

https://docs.pytorch.org/docs/stable/generated/torch.fake_quantize_per_channel_affine.html

input (Tensor) – the input value(s), in torch.float32

Hmm.. seems that the api allows only float32 tensor.