Merge branch 'int8_quantize' into op_capture

src/targets/gpu/device/convert.cpp

@@ -20,10 +20,10 @@ void convert(hipStream_t stream,
             if(target_type == shape::int8_type)
             {
                 gs_launch(stream, result.get_shape().elements())([=](auto i) {
-                    float res  = input_ptr[i] * scale + shift;
-                    int factor = (res > 0) ? 1 : -1;
-                    output_ptr[i] =
-                        std::min<int8_t>(std::max<float>(-128, res + factor * 0.5), 127);
+                    float res     = input_ptr[i] * scale + shift;
+                    int factor    = (res > 0) ? 1 : -1;
+                    output_ptr[i] = static_cast<int8_t>(
+                        std::min<float>(std::max<float>(-128.0f, res + factor * 0.5), 127.0f));
                 });
             }
             else