[AZ-180] Fix INT8 conversion: set FP16 flag alongside INT8 for TensorRT 10.x

In TensorRT 10.x, INT8 conversion requires FP16 to be set as a fallback for
network layers (e.g. normalization ops in detection models) that have no INT8
kernel implementation. Without FP16, build_serialized_network can return None
on Jetson for YOLO-type models. INT8 flag is still the primary precision;
FP16 is only the layer-level fallback within the same engine.

Made-with: Cursor

src/engines/tensorrt_engine.pyx

@@ -158,6 +158,8 @@ cdef class TensorRTEngine(InferenceEngine):
                 constants_inf.log(<str>'Converting to INT8 with calibration cache')
                 calibrator = _CacheCalibrator(calib_cache_path)
                 config.set_flag(trt.BuilderFlag.INT8)
+                if builder.platform_has_fast_fp16:
+                    config.set_flag(trt.BuilderFlag.FP16)
                 config.int8_calibrator = calibrator
             elif builder.platform_has_fast_fp16:
                 constants_inf.log(<str>'Converting to supported fp16')

tests/test_az180_jetson_int8.py

@@ -73,6 +73,7 @@ def test_convert_from_source_uses_int8_when_cache_provided():
 
         # Assert
         mock_config.set_flag.assert_any_call("INT8")
+        mock_config.set_flag.assert_any_call("FP16")
         assert mock_config.int8_calibrator is not None
     finally:
         os.unlink(cache_path)