| 1212 | |
| 1213 | template <typename T, typename U> |
| 1214 | void dispatch_quantize( |
| 1215 | const array& w, |
| 1216 | array& out, |
| 1217 | array& scales, |
| 1218 | array& biases, |
| 1219 | int bits, |
| 1220 | int group_size) { |
| 1221 | auto w_ptr = w.data<T>(); |
| 1222 | auto out_ptr = out.data<U>(); |
| 1223 | auto scales_ptr = scales.data<T>(); |
| 1224 | auto biases_ptr = biases.data<T>(); |
| 1225 | quantize<T, U>( |
| 1226 | w_ptr, out_ptr, scales_ptr, biases_ptr, bits, group_size, w.size()); |
| 1227 | } |
| 1228 | |
| 1229 | void fast::Quantize::eval_cpu( |
| 1230 | const std::vector<array>& inputs, |