v0.42.0

See https://github.com/quic/ai-hub-models/releases/v0.42.0 for changelog.

NASNet_float.tflite

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:f42f28b02c45e7989bb2a6ed89cfd1ac445fa4b0dd24813ed5cde6dc20d1052e
-size 354842664
+oid sha256:f2f875a81085a29b35d817bdadaabbeb6ded9170a0e43205fec250ac55fcc649
+size 354843808

README.md

@@ -38,13 +38,13 @@ More details on model performance across various devices, can be found
 
 | Model | Precision | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit | Target Model
 |---|---|---|---|---|---|---|---|---|
-| NASNet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 37.302 ms | 0 - 315 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
-| NASNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 14.947 ms | 0 - 323 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
-| NASNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 7.522 ms | 0 - 32 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
-| NASNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 10.61 ms | 0 - 313 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
-| NASNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.57 ms | 0 - 367 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
-| NASNet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 4.59 ms | 0 - 313 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
-| NASNet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 4.074 ms | 0 - 311 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 37.326 ms | 0 - 318 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 14.889 ms | 0 - 326 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 7.485 ms | 0 - 26 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 10.589 ms | 0 - 317 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 5.43 ms | 0 - 371 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | Samsung Galaxy S25 | Snapdragon® 8 Elite For Galaxy Mobile | TFLITE | 4.679 ms | 0 - 314 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
+| NASNet | float | Snapdragon 8 Elite Gen 5 QRD | Snapdragon® 8 Elite Gen5 Mobile | TFLITE | 4.059 ms | 0 - 313 MB | NPU | [NASNet.tflite](https://huggingface.co/qualcomm/NASNet/blob/main/NASNet.tflite) |
 
 
 
@@ -59,9 +59,9 @@ pip install "qai-hub-models[nasnet]"
 ```
 
 
-## Configure Qualcomm® AI Hub to run this model on a cloud-hosted device
+## Configure Qualcomm® AI Hub Workbench to run this model on a cloud-hosted device
 
-Sign-in to [Qualcomm® AI Hub](https://app.aihub.qualcomm.com/) with your
+Sign-in to [Qualcomm® AI Hub Workbench](https://workbench.aihub.qualcomm.com/) with your
 Qualcomm® ID. Once signed in navigate to `Account -> Settings -> API Token`.
 
 With this API token, you can configure your client to run models on the cloud
@@ -69,7 +69,7 @@ hosted devices.
 ```bash
 qai-hub configure --api_token API_TOKEN
 ```
-Navigate to [docs](https://app.aihub.qualcomm.com/docs/) for more information.
+Navigate to [docs](https://workbench.aihub.qualcomm.com/docs/) for more information.
 
 
 
@@ -180,7 +180,7 @@ With the output of the model, you can compute like PSNR, relative errors or
 spot check the output with expected output.
 
 **Note**: This on-device profiling and inference requires access to Qualcomm®
-AI Hub. [Sign up for access](https://myaccount.qualcomm.com/signup).
+AI Hub Workbench. [Sign up for access](https://myaccount.qualcomm.com/signup).
 
 
 

tool-versions.yaml

@@ -1,4 +1,4 @@
 tool_versions:
   tflite:
-    qairt: 2.39.0.250925215840_163802
+    qairt: 2.40.0.251030114326_189385
     tflite: 2.17.0