qaihm-bot commited on
Commit
1e568ec
·
verified ·
1 Parent(s): 4eca8df

See https://github.com/qualcomm/ai-hub-models/releases/v0.51.0 for changelog.

Files changed (2) hide show
  1. README.md +108 -78
  2. release_assets.json +81 -1
README.md CHANGED
@@ -28,13 +28,15 @@ Below are pre-exported model assets ready for deployment.
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
- | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.50.2/vit-onnx-float.zip)
32
- | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.50.2/vit-onnx-w8a16.zip)
33
- | ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.50.2/vit-onnx-w8a8.zip)
34
- | ONNX | w8a8_mixed_int16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.50.2/vit-onnx-w8a8_mixed_int16.zip)
35
- | QNN_DLC | float | Universal | QAIRT 2.43 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.50.2/vit-qnn_dlc-float.zip)
36
- | TFLITE | float | Universal | QAIRT 2.43, TFLite 2.19.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.50.2/vit-tflite-float.zip)
37
- | TFLITE | w8a8 | Universal | QAIRT 2.43, TFLite 2.19.1 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.50.2/vit-tflite-w8a8.zip)
 
 
38
 
39
  For more device-specific assets and performance metrics, visit **[VIT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/vit)**.
40
 
@@ -65,77 +67,105 @@ See our repository for [VIT on GitHub](https://github.com/qualcomm/ai-hub-models
65
  ## Performance Summary
66
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
67
  |---|---|---|---|---|---|---
68
- | VIT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.698 ms | 1 - 347 MB | NPU
69
- | VIT | ONNX | float | Snapdragon® X2 Elite | 3.028 ms | 170 - 170 MB | NPU
70
- | VIT | ONNX | float | Snapdragon® X Elite | 7.669 ms | 170 - 170 MB | NPU
71
- | VIT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.03 ms | 0 - 369 MB | NPU
72
- | VIT | ONNX | float | Qualcomm® QCS8550 (Proxy) | 7.131 ms | 0 - 196 MB | NPU
73
- | VIT | ONNX | float | Qualcomm® QCS9075 | 10.169 ms | 0 - 4 MB | NPU
74
- | VIT | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.44 ms | 0 - 339 MB | NPU
75
- | VIT | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.116 ms | 0 - 276 MB | NPU
76
- | VIT | ONNX | w8a16 | Snapdragon® X2 Elite | 4.424 ms | 86 - 86 MB | NPU
77
- | VIT | ONNX | w8a16 | Snapdragon® X Elite | 8.794 ms | 86 - 86 MB | NPU
78
- | VIT | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.734 ms | 0 - 349 MB | NPU
79
- | VIT | ONNX | w8a16 | Qualcomm® QCS6490 | 1125.779 ms | 31 - 54 MB | CPU
80
- | VIT | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 8.19 ms | 0 - 102 MB | NPU
81
- | VIT | ONNX | w8a16 | Qualcomm® QCS9075 | 8.771 ms | 0 - 3 MB | NPU
82
- | VIT | ONNX | w8a16 | Qualcomm® QCM6690 | 604.448 ms | 54 - 70 MB | CPU
83
- | VIT | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.395 ms | 0 - 281 MB | NPU
84
- | VIT | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 590.731 ms | 42 - 59 MB | CPU
85
- | VIT | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 4.576 ms | 0 - 421 MB | NPU
86
- | VIT | ONNX | w8a8 | Snapdragon® X2 Elite | 5.214 ms | 85 - 85 MB | NPU
87
- | VIT | ONNX | w8a8 | Snapdragon® X Elite | 13.707 ms | 85 - 85 MB | NPU
88
- | VIT | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 8.762 ms | 0 - 530 MB | NPU
89
- | VIT | ONNX | w8a8 | Qualcomm® QCS6490 | 308.621 ms | 19 - 72 MB | CPU
90
- | VIT | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 12.993 ms | 0 - 101 MB | NPU
91
- | VIT | ONNX | w8a8 | Qualcomm® QCS9075 | 13.737 ms | 0 - 3 MB | NPU
92
- | VIT | ONNX | w8a8 | Qualcomm® QCM6690 | 131.058 ms | 22 - 41 MB | CPU
93
- | VIT | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 6.966 ms | 0 - 413 MB | NPU
94
- | VIT | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 125.982 ms | 11 - 31 MB | CPU
95
- | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® X2 Elite | 45.84 ms | 75 - 75 MB | NPU
96
- | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® X Elite | 160.974 ms | 73 - 73 MB | NPU
97
- | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 74.098 ms | 54 - 418 MB | NPU
98
- | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® QCS6490 | 729.381 ms | 77 - 111 MB | CPU
99
- | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® QCS8550 (Proxy) | 93.613 ms | 51 - 57 MB | NPU
100
- | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® QCS9075 | 115.883 ms | 55 - 57 MB | NPU
101
- | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® QCM6690 | 363.109 ms | 41 - 61 MB | CPU
102
- | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite For Galaxy Mobile | 63.713 ms | 51 - 335 MB | NPU
103
- | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 352.78 ms | 81 - 104 MB | CPU
104
- | VIT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.993 ms | 0 - 318 MB | NPU
105
- | VIT | QNN_DLC | float | Snapdragon® X2 Elite | 3.572 ms | 1 - 1 MB | NPU
106
- | VIT | QNN_DLC | float | Snapdragon® X Elite | 8.504 ms | 1 - 1 MB | NPU
107
- | VIT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.519 ms | 0 - 357 MB | NPU
108
- | VIT | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 35.226 ms | 1 - 331 MB | NPU
109
- | VIT | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 7.912 ms | 1 - 2 MB | NPU
110
- | VIT | QNN_DLC | float | Qualcomm® SA8775P | 10.654 ms | 1 - 332 MB | NPU
111
- | VIT | QNN_DLC | float | Qualcomm® QCS9075 | 11.097 ms | 1 - 3 MB | NPU
112
- | VIT | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 12.772 ms | 0 - 337 MB | NPU
113
- | VIT | QNN_DLC | float | Qualcomm® SA7255P | 35.226 ms | 1 - 331 MB | NPU
114
- | VIT | QNN_DLC | float | Qualcomm® SA8295P | 13.047 ms | 1 - 310 MB | NPU
115
- | VIT | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.759 ms | 0 - 333 MB | NPU
116
- | VIT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.955 ms | 0 - 275 MB | NPU
117
- | VIT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.276 ms | 0 - 355 MB | NPU
118
- | VIT | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 34.552 ms | 0 - 276 MB | NPU
119
- | VIT | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 7.191 ms | 0 - 3 MB | NPU
120
- | VIT | TFLITE | float | Qualcomm® SA8775P | 10.187 ms | 0 - 277 MB | NPU
121
- | VIT | TFLITE | float | Qualcomm® QCS9075 | 10.641 ms | 0 - 174 MB | NPU
122
- | VIT | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 12.92 ms | 0 - 339 MB | NPU
123
- | VIT | TFLITE | float | Qualcomm® SA7255P | 34.552 ms | 0 - 276 MB | NPU
124
- | VIT | TFLITE | float | Qualcomm® SA8295P | 13.247 ms | 0 - 265 MB | NPU
125
- | VIT | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.701 ms | 0 - 285 MB | NPU
126
- | VIT | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 4.525 ms | 0 - 381 MB | NPU
127
- | VIT | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 8.662 ms | 0 - 493 MB | NPU
128
- | VIT | TFLITE | w8a8 | Qualcomm® QCS6490 | 166.626 ms | 1 - 101 MB | NPU
129
- | VIT | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 35.043 ms | 0 - 386 MB | NPU
130
- | VIT | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 12.909 ms | 0 - 2 MB | NPU
131
- | VIT | TFLITE | w8a8 | Qualcomm® SA8775P | 12.203 ms | 0 - 388 MB | NPU
132
- | VIT | TFLITE | w8a8 | Qualcomm® QCS9075 | 13.759 ms | 0 - 88 MB | NPU
133
- | VIT | TFLITE | w8a8 | Qualcomm® QCM6690 | 199.256 ms | 2 - 293 MB | NPU
134
- | VIT | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 20.024 ms | 0 - 456 MB | NPU
135
- | VIT | TFLITE | w8a8 | Qualcomm® SA7255P | 35.043 ms | 0 - 386 MB | NPU
136
- | VIT | TFLITE | w8a8 | Qualcomm® SA8295P | 19.189 ms | 0 - 344 MB | NPU
137
- | VIT | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 6.932 ms | 0 - 381 MB | NPU
138
- | VIT | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 29.256 ms | 2 - 222 MB | NPU
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
139
 
140
  ## License
141
  * The license for the original implementation of VIT can be found
 
28
 
29
  | Runtime | Precision | Chipset | SDK Versions | Download |
30
  |---|---|---|---|---|
31
+ | ONNX | float | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.51.0/vit-onnx-float.zip)
32
+ | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.51.0/vit-onnx-w8a16.zip)
33
+ | ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.51.0/vit-onnx-w8a8.zip)
34
+ | ONNX | w8a8_mixed_int16 | Universal | QAIRT 2.42, ONNX Runtime 1.24.3 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.51.0/vit-onnx-w8a8_mixed_int16.zip)
35
+ | QNN_DLC | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.51.0/vit-qnn_dlc-float.zip)
36
+ | QNN_DLC | w8a16 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.51.0/vit-qnn_dlc-w8a16.zip)
37
+ | QNN_DLC | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.51.0/vit-qnn_dlc-w8a8.zip)
38
+ | TFLITE | float | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.51.0/vit-tflite-float.zip)
39
+ | TFLITE | w8a8 | Universal | QAIRT 2.45 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.51.0/vit-tflite-w8a8.zip)
40
 
41
  For more device-specific assets and performance metrics, visit **[VIT on Qualcomm® AI Hub](https://aihub.qualcomm.com/models/vit)**.
42
 
 
67
  ## Performance Summary
68
  | Model | Runtime | Precision | Chipset | Inference Time (ms) | Peak Memory Range (MB) | Primary Compute Unit
69
  |---|---|---|---|---|---|---
70
+ | VIT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.662 ms | 0 - 354 MB | NPU
71
+ | VIT | ONNX | float | Snapdragon® X2 Elite | 3.873 ms | 170 - 170 MB | NPU
72
+ | VIT | ONNX | float | Snapdragon® X Elite | 11.128 ms | 170 - 170 MB | NPU
73
+ | VIT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 7.171 ms | 0 - 377 MB | NPU
74
+ | VIT | ONNX | float | Qualcomm® QCS8550 (Proxy) | 10.454 ms | 0 - 195 MB | NPU
75
+ | VIT | ONNX | float | Qualcomm® QCS9075 | 14.697 ms | 0 - 4 MB | NPU
76
+ | VIT | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 4.99 ms | 0 - 348 MB | NPU
77
+ | VIT | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.775 ms | 0 - 303 MB | NPU
78
+ | VIT | ONNX | w8a16 | Snapdragon® X2 Elite | 3.902 ms | 86 - 86 MB | NPU
79
+ | VIT | ONNX | w8a16 | Snapdragon® X Elite | 11.253 ms | 86 - 86 MB | NPU
80
+ | VIT | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 7.363 ms | 0 - 378 MB | NPU
81
+ | VIT | ONNX | w8a16 | Qualcomm® QCS6490 | 1117.068 ms | 38 - 59 MB | CPU
82
+ | VIT | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 10.668 ms | 0 - 101 MB | NPU
83
+ | VIT | ONNX | w8a16 | Qualcomm® QCS9075 | 12.939 ms | 0 - 3 MB | NPU
84
+ | VIT | ONNX | w8a16 | Qualcomm® QCM6690 | 611.108 ms | 73 - 88 MB | CPU
85
+ | VIT | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 5.314 ms | 0 - 300 MB | NPU
86
+ | VIT | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 593.078 ms | 60 - 76 MB | CPU
87
+ | VIT | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 4.582 ms | 0 - 351 MB | NPU
88
+ | VIT | ONNX | w8a8 | Snapdragon® X2 Elite | 5.101 ms | 85 - 85 MB | NPU
89
+ | VIT | ONNX | w8a8 | Snapdragon® X Elite | 13.62 ms | 85 - 85 MB | NPU
90
+ | VIT | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 8.792 ms | 0 - 457 MB | NPU
91
+ | VIT | ONNX | w8a8 | Qualcomm® QCS6490 | 316.911 ms | 21 - 74 MB | CPU
92
+ | VIT | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 12.93 ms | 0 - 100 MB | NPU
93
+ | VIT | ONNX | w8a8 | Qualcomm® QCS9075 | 13.549 ms | 0 - 3 MB | NPU
94
+ | VIT | ONNX | w8a8 | Qualcomm® QCM6690 | 136.498 ms | 21 - 42 MB | CPU
95
+ | VIT | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 7.243 ms | 0 - 323 MB | NPU
96
+ | VIT | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 129.249 ms | 22 - 43 MB | CPU
97
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite Gen 5 Mobile | 62.922 ms | 21 - 289 MB | NPU
98
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® X2 Elite | 56.849 ms | 79 - 79 MB | NPU
99
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® X Elite | 160.029 ms | 79 - 79 MB | NPU
100
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 85.742 ms | 69 - 445 MB | NPU
101
+ | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® QCS6490 | 733.594 ms | 96 - 128 MB | CPU
102
+ | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® QCS8550 (Proxy) | 100.182 ms | 9 - 95 MB | NPU
103
+ | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® QCS9075 | 130.409 ms | 68 - 70 MB | NPU
104
+ | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® QCM6690 | 383.515 ms | 99 - 121 MB | CPU
105
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite For Galaxy Mobile | 72.88 ms | 68 - 339 MB | NPU
106
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 373.213 ms | 95 - 114 MB | CPU
107
+ | VIT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 4.094 ms | 1 - 231 MB | NPU
108
+ | VIT | QNN_DLC | float | Snapdragon® X2 Elite | 4.45 ms | 1 - 1 MB | NPU
109
+ | VIT | QNN_DLC | float | Snapdragon® X Elite | 11.889 ms | 1 - 1 MB | NPU
110
+ | VIT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 7.675 ms | 0 - 310 MB | NPU
111
+ | VIT | QNN_DLC | float | Qualcomm® QCS8275 (Proxy) | 40.628 ms | 1 - 177 MB | NPU
112
+ | VIT | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 11.19 ms | 1 - 2 MB | NPU
113
+ | VIT | QNN_DLC | float | Qualcomm® SA8775P | 13.991 ms | 1 - 213 MB | NPU
114
+ | VIT | QNN_DLC | float | Qualcomm® QCS9075 | 15.487 ms | 1 - 3 MB | NPU
115
+ | VIT | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 19.142 ms | 0 - 291 MB | NPU
116
+ | VIT | QNN_DLC | float | Qualcomm® SA7255P | 40.628 ms | 1 - 177 MB | NPU
117
+ | VIT | QNN_DLC | float | Qualcomm® SA8295P | 17.287 ms | 0 - 192 MB | NPU
118
+ | VIT | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 5.381 ms | 1 - 224 MB | NPU
119
+ | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.374 ms | 0 - 298 MB | NPU
120
+ | VIT | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 4.184 ms | 0 - 0 MB | NPU
121
+ | VIT | QNN_DLC | w8a16 | Snapdragon® X Elite | 9.853 ms | 0 - 0 MB | NPU
122
+ | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 6.444 ms | 0 - 345 MB | NPU
123
+ | VIT | QNN_DLC | w8a16 | Qualcomm® QCS8275 (Proxy) | 20.24 ms | 0 - 284 MB | NPU
124
+ | VIT | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 9.034 ms | 0 - 287 MB | NPU
125
+ | VIT | QNN_DLC | w8a16 | Qualcomm® SA8775P | 9.402 ms | 0 - 285 MB | NPU
126
+ | VIT | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 11.506 ms | 0 - 2 MB | NPU
127
+ | VIT | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 87.029 ms | 0 - 413 MB | NPU
128
+ | VIT | QNN_DLC | w8a16 | Qualcomm® SA7255P | 20.24 ms | 0 - 284 MB | NPU
129
+ | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.758 ms | 0 - 283 MB | NPU
130
+ | VIT | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 15.216 ms | 0 - 428 MB | NPU
131
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.706 ms | 0 - 279 MB | NPU
132
+ | VIT | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 4.573 ms | 0 - 0 MB | NPU
133
+ | VIT | QNN_DLC | w8a8 | Snapdragon® X Elite | 10.754 ms | 0 - 0 MB | NPU
134
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 7.069 ms | 0 - 411 MB | NPU
135
+ | VIT | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 51.044 ms | 0 - 2 MB | NPU
136
+ | VIT | QNN_DLC | w8a8 | Qualcomm® QCS8275 (Proxy) | 29.699 ms | 0 - 287 MB | NPU
137
+ | VIT | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 10.229 ms | 0 - 2 MB | NPU
138
+ | VIT | QNN_DLC | w8a8 | Qualcomm® SA8775P | 9.342 ms | 0 - 288 MB | NPU
139
+ | VIT | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 9.918 ms | 2 - 4 MB | NPU
140
+ | VIT | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 248.567 ms | 0 - 499 MB | NPU
141
+ | VIT | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 13.452 ms | 0 - 414 MB | NPU
142
+ | VIT | QNN_DLC | w8a8 | Qualcomm® SA7255P | 29.699 ms | 0 - 287 MB | NPU
143
+ | VIT | QNN_DLC | w8a8 | Qualcomm® SA8295P | 16.067 ms | 0 - 188 MB | NPU
144
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 5.79 ms | 0 - 289 MB | NPU
145
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 20.043 ms | 0 - 325 MB | NPU
146
+ | VIT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.029 ms | 0 - 174 MB | NPU
147
+ | VIT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.698 ms | 0 - 274 MB | NPU
148
+ | VIT | TFLITE | float | Qualcomm® QCS8275 (Proxy) | 35.349 ms | 0 - 187 MB | NPU
149
+ | VIT | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 7.866 ms | 0 - 3 MB | NPU
150
+ | VIT | TFLITE | float | Qualcomm® SA8775P | 10.791 ms | 0 - 190 MB | NPU
151
+ | VIT | TFLITE | float | Qualcomm® QCS9075 | 11.475 ms | 0 - 173 MB | NPU
152
+ | VIT | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 13.903 ms | 0 - 241 MB | NPU
153
+ | VIT | TFLITE | float | Qualcomm® SA7255P | 35.349 ms | 0 - 187 MB | NPU
154
+ | VIT | TFLITE | float | Qualcomm® SA8295P | 13.431 ms | 0 - 154 MB | NPU
155
+ | VIT | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.908 ms | 0 - 184 MB | NPU
156
+ | VIT | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 4.569 ms | 0 - 334 MB | NPU
157
+ | VIT | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 8.776 ms | 0 - 457 MB | NPU
158
+ | VIT | TFLITE | w8a8 | Qualcomm® QCS6490 | 152.222 ms | 1 - 101 MB | NPU
159
+ | VIT | TFLITE | w8a8 | Qualcomm® QCS8275 (Proxy) | 35.43 ms | 0 - 327 MB | NPU
160
+ | VIT | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 12.279 ms | 0 - 4 MB | NPU
161
+ | VIT | TFLITE | w8a8 | Qualcomm® SA8775P | 12.377 ms | 0 - 327 MB | NPU
162
+ | VIT | TFLITE | w8a8 | Qualcomm® QCS9075 | 13.843 ms | 0 - 88 MB | NPU
163
+ | VIT | TFLITE | w8a8 | Qualcomm® QCM6690 | 203.01 ms | 2 - 287 MB | NPU
164
+ | VIT | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 21.722 ms | 0 - 446 MB | NPU
165
+ | VIT | TFLITE | w8a8 | Qualcomm® SA7255P | 35.43 ms | 0 - 327 MB | NPU
166
+ | VIT | TFLITE | w8a8 | Qualcomm® SA8295P | 19.859 ms | 0 - 318 MB | NPU
167
+ | VIT | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 7.09 ms | 0 - 317 MB | NPU
168
+ | VIT | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 30.808 ms | 2 - 191 MB | NPU
169
 
170
  ## License
171
  * The license for the original implementation of VIT can be found
release_assets.json CHANGED
@@ -1 +1,81 @@
1
- {"version":"0.50.2","precisions":{"float":{"universal_assets":{"onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.50.2/vit-onnx-float.zip"},"qnn_dlc":{"tool_versions":{"qairt":"2.43.0.260127150333_193827"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.50.2/vit-qnn_dlc-float.zip"},"tflite":{"tool_versions":{"qairt":"2.43.0.260127150333_193827","tflite":"2.19.1"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.50.2/vit-tflite-float.zip"}}},"w8a16":{"universal_assets":{"onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.50.2/vit-onnx-w8a16.zip"}}},"w8a8":{"universal_assets":{"onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.50.2/vit-onnx-w8a8.zip"},"tflite":{"tool_versions":{"qairt":"2.43.0.260127150333_193827","tflite":"2.19.1"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.50.2/vit-tflite-w8a8.zip"}}},"w8a8_mixed_int16":{"universal_assets":{"onnx":{"tool_versions":{"qairt":"2.42.0.251225135753_193295","onnx_runtime":"1.24.3"},"download_url":"https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.50.2/vit-onnx-w8a8_mixed_int16.zip"}}}}}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "0.51.0",
3
+ "precisions": {
4
+ "w8a8": {
5
+ "universal_assets": {
6
+ "tflite": {
7
+ "tool_versions": {
8
+ "qairt": "2.45.0.260326154327",
9
+ "litert": "1.4.2"
10
+ },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.51.0/vit-tflite-w8a8.zip"
12
+ },
13
+ "qnn_dlc": {
14
+ "tool_versions": {
15
+ "qairt": "2.45.0.260326154327"
16
+ },
17
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.51.0/vit-qnn_dlc-w8a8.zip"
18
+ },
19
+ "onnx": {
20
+ "tool_versions": {
21
+ "qairt": "2.42.0.251225135753_193295",
22
+ "onnx_runtime": "1.24.3"
23
+ },
24
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.51.0/vit-onnx-w8a8.zip"
25
+ }
26
+ }
27
+ },
28
+ "w8a8_mixed_int16": {
29
+ "universal_assets": {
30
+ "onnx": {
31
+ "tool_versions": {
32
+ "qairt": "2.42.0.251225135753_193295",
33
+ "onnx_runtime": "1.24.3"
34
+ },
35
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.51.0/vit-onnx-w8a8_mixed_int16.zip"
36
+ }
37
+ }
38
+ },
39
+ "w8a16": {
40
+ "universal_assets": {
41
+ "qnn_dlc": {
42
+ "tool_versions": {
43
+ "qairt": "2.45.0.260326154327"
44
+ },
45
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.51.0/vit-qnn_dlc-w8a16.zip"
46
+ },
47
+ "onnx": {
48
+ "tool_versions": {
49
+ "qairt": "2.42.0.251225135753_193295",
50
+ "onnx_runtime": "1.24.3"
51
+ },
52
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.51.0/vit-onnx-w8a16.zip"
53
+ }
54
+ }
55
+ },
56
+ "float": {
57
+ "universal_assets": {
58
+ "tflite": {
59
+ "tool_versions": {
60
+ "qairt": "2.45.0.260326154327",
61
+ "litert": "1.4.2"
62
+ },
63
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.51.0/vit-tflite-float.zip"
64
+ },
65
+ "qnn_dlc": {
66
+ "tool_versions": {
67
+ "qairt": "2.45.0.260326154327"
68
+ },
69
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.51.0/vit-qnn_dlc-float.zip"
70
+ },
71
+ "onnx": {
72
+ "tool_versions": {
73
+ "qairt": "2.42.0.251225135753_193295",
74
+ "onnx_runtime": "1.24.3"
75
+ },
76
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.51.0/vit-onnx-float.zip"
77
+ }
78
+ }
79
+ }
80
+ }
81
+ }