v0.34.0

See https://github.com/quic/ai-hub-models/releases/v0.34.0 for changelog.

README.md

@@ -25,6 +25,7 @@ More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/efficientvit_b2_cls).
 
 
+
 ### Model Details
 
 - **Model Type:** Model_use_case.image_classification
@@ -36,21 +37,21 @@ 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
 |---|---|---|---|---|---|---|---|---|
-| EfficientViT-b2-cls | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 50.868 ms | 0 - 112 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
+| EfficientViT-b2-cls | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 12.076 ms | 0 - 113 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
 | EfficientViT-b2-cls | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 12.47 ms | 1 - 61 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
-| EfficientViT-b2-cls | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 5.945 ms | 0 - 117 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
+| EfficientViT-b2-cls | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 5.842 ms | 0 - 117 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
 | EfficientViT-b2-cls | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 6.897 ms | 1 - 69 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
-| EfficientViT-b2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 5.004 ms | 0 - 267 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
+| EfficientViT-b2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 4.933 ms | 0 - 341 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
 | EfficientViT-b2-cls | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 5.151 ms | 0 - 16 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
-| EfficientViT-b2-cls | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 6.014 ms | 0 - 112 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
+| EfficientViT-b2-cls | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 6.046 ms | 0 - 112 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
 | EfficientViT-b2-cls | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 6.616 ms | 1 - 61 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
-| EfficientViT-b2-cls | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 5.009 ms | 0 - 339 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
+| EfficientViT-b2-cls | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 4.957 ms | 0 - 365 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
 | EfficientViT-b2-cls | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 5.255 ms | 0 - 16 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
 | EfficientViT-b2-cls | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 5.409 ms | 0 - 124 MB | NPU | [EfficientViT-b2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx) |
-| EfficientViT-b2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 3.437 ms | 0 - 125 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
+| EfficientViT-b2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 3.444 ms | 0 - 129 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
 | EfficientViT-b2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 3.647 ms | 1 - 76 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
 | EfficientViT-b2-cls | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 3.71 ms | 0 - 79 MB | NPU | [EfficientViT-b2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx) |
-| EfficientViT-b2-cls | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 3.323 ms | 0 - 115 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
+| EfficientViT-b2-cls | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 2.835 ms | 0 - 116 MB | NPU | [EfficientViT-b2-cls.tflite](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.tflite) |
 | EfficientViT-b2-cls | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 3.111 ms | 1 - 65 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
 | EfficientViT-b2-cls | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 3.252 ms | 1 - 64 MB | NPU | [EfficientViT-b2-cls.onnx](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.onnx) |
 | EfficientViT-b2-cls | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 6.803 ms | 300 - 300 MB | NPU | [EfficientViT-b2-cls.dlc](https://huggingface.co/qualcomm/EfficientViT-b2-cls/blob/main/EfficientViT-b2-cls.dlc) |
@@ -112,17 +113,7 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.efficientvit_b2_cls.export
 ```
-```
-Profiling Results
-------------------------------------------------------------
-EfficientViT-b2-cls
-Device                          : cs_8275 (ANDROID 14)                 
-Runtime                         : TFLITE                               
-Estimated inference time (ms)   : 50.9                                 
-Estimated peak memory usage (MB): [0, 112]                             
-Total # Ops                     : 379                                  
-Compute Unit(s)                 : npu (379 ops) gpu (0 ops) cpu (0 ops)
-```
+
 
 
 ## How does this work?

precompiled/qualcomm-snapdragon-x-elite/EfficientViT-b2-cls.onnx.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2bc95c76b7b1ba6c182ad794c18dd3a659ddd0473f97b9b5ab445e05b4eb76f2
-size 45623041
+oid sha256:45e01226f16de4312da89421c77af355e2124cd2d612f48720af7e32ad367763
+size 45623040

precompiled/qualcomm-snapdragon-x-elite/sdk_versions.yml

@@ -0,0 +1,5 @@
+sdk_versions:
+  qnn_context_binary:
+    qairt: 2.34.2.250528164111_119506
+  precompiled_qnn_onnx:
+    qairt: 2.33.2.250410134701_117956