Update README.md

README.md

@@ -50,6 +50,13 @@ compilation; they do not contain device-specific compiled NPU programs.
   substantial accuracy tradeoff and retains INT16 regions, so backend support
   must be verified.
 
+Extra notes: Apple ANE and QC NPUs support FP16 natively and the performances are
+usually very good. Deloying a FP16 model is much easier since it does not require
+calibration steps. Note that the A16W8 and A8W8 assets provided here were calibrated
+from a particular dataset and should not used in production directly. A FP16 model
+file is not provided here is because it is easy to be generated from the fp32 asset. 
+It is actually a top choice. 
+
 ## TorchAO quantization recipe
 
 Both variants use post-training static quantization, without QAT or fine-tuning.
@@ -158,7 +165,7 @@ value is the median of three process means, with five warmup invocations and
 30 measured invocations per process. All configurations are AOT compiled and
 fully delegated to the NPU, with no residual CPU operations.
 
-| Model file | `SM-S937U1`, Qualcomm SM8750 (ms) | `LJ9`, MediaTek MT6897 (ms) |
+| Model file | `SM-S937U1`(ms) | `LJ9`(ms) |
 | --- | ---: | ---: |
 | `model_fp32.tflite` | 6 | 129 |
 | `model_a16w8.tflite` | 4 | 71 |
@@ -174,8 +181,8 @@ preprocessing, file I/O and explicit host input/output buffer transfers.
 Some variants were measured in separate sessions using the same benchmark
 and dispatch runtime for each device.
 
-The Samsung ran Android 17 with Qualcomm QNN/QAIRT 2.50 in burst performance
-mode. The TECNO ran Android 15 with the MediaTek Neuron runtime in sustained
+The `SM-S937U1` ran Android 17 with Qualcomm QNN/QAIRT 2.50 in burst performance
+mode. The LJ9 ran Android 15 with the MediaTek Neuron runtime in sustained
 speed mode. Power settings were not normalized, and energy consumption was
 not measured. These results apply to the listed device/compiler/runtime
 combinations and do not characterize JIT performance.