[AWQ] Cast fns.quantile() result to float32

[nikita-savelyevv]

Changes

Cast fns.quantile() result to float32 inside AWQ algorithm.

Reason for changes

fns.quantile() for numpy backend returns np.float64 value. In AWQ it is used as a clip lower bound, resulting in float64 result. Then via chain reaction it leads to weights and activations being converted to float64.

As I understand, processing in float64 is not necessary. At the same time it leads to increased running time. Below are measurements for compression time with AWQ enabled before and after the changes.

Model	develop (sec.)	branch (sec.)
tiny-llama-1.1b	123	109 (-11%)
phi3_mini-3.7b	487	419 (-14%)
llama3-8b	1091	912 (-16%)

[nikita-savelyevv]

Post-training weight compression conformance test shows no accuracy degradations (NNCF/job/manual/job/post_training_weight_compression/229). I've compared against develop build 230.