v0.34.0

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

README.md

@@ -24,6 +24,7 @@ More details on model performance across various devices, can be found
 [here](https://aihub.qualcomm.com/models/openai_clip).
 
 
+
 ### Model Details
 
 - **Model Type:** Model_use_case.image_classification
@@ -36,31 +37,31 @@ 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
 |---|---|---|---|---|---|---|---|---|
-| OpenAI-Clip | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 71.105 ms | 0 - 407 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
+| OpenAI-Clip | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 70.94 ms | 0 - 407 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
 | OpenAI-Clip | float | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 58.433 ms | 1 - 481 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
-| OpenAI-Clip | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 26.259 ms | 0 - 360 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
+| OpenAI-Clip | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 26.126 ms | 0 - 359 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
 | OpenAI-Clip | float | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 22.93 ms | 1 - 452 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
-| OpenAI-Clip | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 23.733 ms | 0 - 117 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
+| OpenAI-Clip | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 23.098 ms | 0 - 81 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
 | OpenAI-Clip | float | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | QNN_DLC | 19.924 ms | 0 - 53 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
-| OpenAI-Clip | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 28.475 ms | 0 - 407 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
+| OpenAI-Clip | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | TFLITE | 28.575 ms | 0 - 407 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
 | OpenAI-Clip | float | QCS9075 (Proxy) | Qualcomm® QCS9075 (Proxy) | QNN_DLC | 22.704 ms | 0 - 484 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
-| OpenAI-Clip | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 71.105 ms | 0 - 407 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
+| OpenAI-Clip | float | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 70.94 ms | 0 - 407 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
 | OpenAI-Clip | float | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 58.433 ms | 1 - 481 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
-| OpenAI-Clip | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 23.741 ms | 0 - 51 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
+| OpenAI-Clip | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 23.587 ms | 0 - 72 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
 | OpenAI-Clip | float | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 19.803 ms | 0 - 55 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
-| OpenAI-Clip | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 29.538 ms | 0 - 349 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
+| OpenAI-Clip | float | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 29.464 ms | 0 - 349 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
 | OpenAI-Clip | float | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 23.717 ms | 1 - 479 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
-| OpenAI-Clip | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 23.789 ms | 0 - 33 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
+| OpenAI-Clip | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 24.016 ms | 0 - 26 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
 | OpenAI-Clip | float | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 19.847 ms | 0 - 60 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
-| OpenAI-Clip | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 28.475 ms | 0 - 407 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
+| OpenAI-Clip | float | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 28.575 ms | 0 - 407 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
 | OpenAI-Clip | float | SA8775P ADP | Qualcomm® SA8775P | QNN_DLC | 22.704 ms | 0 - 484 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
-| OpenAI-Clip | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 23.566 ms | 0 - 29 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
+| OpenAI-Clip | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | TFLITE | 23.76 ms | 0 - 26 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
 | OpenAI-Clip | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | QNN_DLC | 19.911 ms | 0 - 57 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
 | OpenAI-Clip | float | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 Mobile | ONNX | 25.037 ms | 1 - 39 MB | NPU | [OpenAI-Clip.onnx](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.onnx) |
-| OpenAI-Clip | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 16.784 ms | 0 - 415 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
+| OpenAI-Clip | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | TFLITE | 16.86 ms | 0 - 413 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
 | OpenAI-Clip | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | QNN_DLC | 14.146 ms | 1 - 491 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
 | OpenAI-Clip | float | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 Mobile | ONNX | 17.712 ms | 0 - 531 MB | NPU | [OpenAI-Clip.onnx](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.onnx) |
-| OpenAI-Clip | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 13.737 ms | 0 - 406 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
+| OpenAI-Clip | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | TFLITE | 15.996 ms | 0 - 406 MB | NPU | [OpenAI-Clip.tflite](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.tflite) |
 | OpenAI-Clip | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | QNN_DLC | 13.268 ms | 1 - 470 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
 | OpenAI-Clip | float | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite Mobile | ONNX | 17.115 ms | 1 - 510 MB | NPU | [OpenAI-Clip.onnx](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.onnx) |
 | OpenAI-Clip | float | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 21.759 ms | 1667 - 1667 MB | NPU | [OpenAI-Clip.dlc](https://huggingface.co/qualcomm/OpenAI-Clip/blob/main/OpenAI-Clip.dlc) |
@@ -122,17 +123,7 @@ device. This script does the following:
 ```bash
 python -m qai_hub_models.models.openai_clip.export
 ```
-```
-Profiling Results
-------------------------------------------------------------
-OpenAI-Clip
-Device                          : cs_8275 (ANDROID 14)                  
-Runtime                         : TFLITE                                
-Estimated inference time (ms)   : 71.1                                  
-Estimated peak memory usage (MB): [0, 407]                              
-Total # Ops                     : 1320                                  
-Compute Unit(s)                 : npu (1318 ops) gpu (0 ops) cpu (2 ops)
-```
+
 
 
 ## How does this work?

precompiled/qualcomm-snapdragon-x-elite/OpenAI-Clip.onnx.zip

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:6e5531d623ca61cf7dd474bdfe01339068595ac73dfc4f909587e9f6c611d5f8
+oid sha256:8da4583071cdc451eaf52d67f1bb5972b5634c5513671333122ecf0f5e8a20c8
 size 278937907

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