Introduce `--int4-weights` option in `migraphx-driver`. This would require changes in MIGraphX's naive quantizer to set range between `[0, 15]` During quantization it should also insert "pack" and "unpack" instructions. #3341
Since its quantizing the weights we dont need to use our quantizer. Instead we would just take the range of weights and compute scale so it fits in the range of [0, 15]. We also need to insert Q/DQ pairs as well.
Since its quantizing the weights we dont need to use our quantizer. Instead we would just take the range of weights and compute scale so it fits in the range of
[0, 15]. We also need to insert Q/DQ pairs as well.