qaihm-bot commited on
Commit
6dce931
·
verified ·
1 Parent(s): 920ab84

See https://github.com/qualcomm/ai-hub-models/releases/v0.56.0 for changelog.

Files changed (2) hide show
  1. README.md +125 -131
  2. release_assets.json +33 -33
README.md CHANGED
@@ -28,15 +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 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.55.0/vit-onnx-float.zip)
32
- | ONNX | w8a16 | Universal | QAIRT 2.42, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.55.0/vit-onnx-w8a16.zip)
33
- | ONNX | w8a8 | Universal | QAIRT 2.42, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.55.0/vit-onnx-w8a8.zip)
34
- | ONNX | w8a8_mixed_int16 | Universal | QAIRT 2.42, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.55.0/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/v0.55.0/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/v0.55.0/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/v0.55.0/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/v0.55.0/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/v0.55.0/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
 
@@ -67,132 +67,126 @@ See our repository for [VIT on GitHub](https://github.com/qualcomm/ai-hub-models
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 | 2.697 ms | 1 - 339 MB | NPU
71
- | VIT | ONNX | float | Snapdragon® X2 Elite | 3.034 ms | 181 - 181 MB | NPU
72
- | VIT | ONNX | float | Snapdragon® X Elite | 7.464 ms | 170 - 170 MB | NPU
73
- | VIT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.029 ms | 1 - 364 MB | NPU
74
- | VIT | ONNX | float | Qualcomm® QCS8550 (Proxy) | 7.121 ms | 0 - 203 MB | NPU
75
- | VIT | ONNX | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.392 ms | 0 - 338 MB | NPU
76
- | VIT | ONNX | float | Qualcomm® QCS9075 | 10.178 ms | 1 - 46 MB | NPU
77
- | VIT | ONNX | float | Qualcomm® QCS8750 | 3.392 ms | 0 - 338 MB | NPU
78
- | VIT | ONNX | float | Qualcomm® QCS7181 | 7.464 ms | 170 - 170 MB | NPU
79
- | VIT | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 3.119 ms | 0 - 288 MB | NPU
80
- | VIT | ONNX | w8a16 | Snapdragon® X2 Elite | 3.182 ms | 182 - 182 MB | NPU
81
- | VIT | ONNX | w8a16 | Snapdragon® X Elite | 8.564 ms | 150 - 150 MB | NPU
82
- | VIT | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.714 ms | 0 - 362 MB | NPU
83
- | VIT | ONNX | w8a16 | Qualcomm® QCS6490 | 1103.987 ms | 45 - 59 MB | CPU
84
- | VIT | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 8.233 ms | 0 - 114 MB | NPU
85
- | VIT | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 578.785 ms | 58 - 74 MB | CPU
86
- | VIT | ONNX | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 4.399 ms | 0 - 281 MB | NPU
87
- | VIT | ONNX | w8a16 | Qualcomm® QCM6690 | 590.634 ms | 98 - 116 MB | CPU
88
- | VIT | ONNX | w8a16 | Qualcomm® QCS9075 | 8.765 ms | 0 - 45 MB | NPU
89
- | VIT | ONNX | w8a16 | Qualcomm® QCS7790 | 578.785 ms | 58 - 74 MB | CPU
90
- | VIT | ONNX | w8a16 | Qualcomm® QCS8750 | 4.399 ms | 0 - 281 MB | NPU
91
- | VIT | ONNX | w8a16 | Qualcomm® QCS7181 | 8.564 ms | 150 - 150 MB | NPU
92
- | VIT | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 4.57 ms | 0 - 425 MB | NPU
93
- | VIT | ONNX | w8a8 | Snapdragon® X Elite | 13.583 ms | 151 - 151 MB | NPU
94
- | VIT | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 8.856 ms | 0 - 537 MB | NPU
95
- | VIT | ONNX | w8a8 | Qualcomm® QCS6490 | 300.53 ms | 20 - 68 MB | CPU
96
- | VIT | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 13.037 ms | 0 - 162 MB | NPU
97
- | VIT | ONNX | w8a8 | Qualcomm® QCS9075 | 13.86 ms | 0 - 45 MB | NPU
98
- | VIT | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 124.909 ms | 36 - 58 MB | CPU
99
- | VIT | ONNX | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 6.999 ms | 0 - 427 MB | NPU
100
- | VIT | ONNX | w8a8 | Qualcomm® QCM6690 | 132.52 ms | 21 - 44 MB | CPU
101
- | VIT | ONNX | w8a8 | Qualcomm® QCS7790 | 124.909 ms | 36 - 58 MB | CPU
102
- | VIT | ONNX | w8a8 | Qualcomm® QCS8750 | 6.999 ms | 0 - 427 MB | NPU
103
- | VIT | ONNX | w8a8 | Qualcomm® QCS7181 | 13.583 ms | 151 - 151 MB | NPU
104
- | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite Gen 5 Mobile | 50.474 ms | 47 - 345 MB | NPU
105
- | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 69.609 ms | 57 - 452 MB | NPU
106
- | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® QCS6490 | 758.29 ms | 99 - 128 MB | CPU
107
- | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® QCS9075 | 105.247 ms | 52 - 110 MB | NPU
108
- | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 7 Gen 4 Mobile | 380.895 ms | 92 - 115 MB | CPU
109
- | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite For Galaxy Mobile | 59.936 ms | 60 - 340 MB | NPU
110
- | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® QCM6690 | 395.353 ms | 103 - 124 MB | CPU
111
- | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® QCS7790 | 380.895 ms | 92 - 115 MB | CPU
112
- | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® QCS8750 | 59.936 ms | 60 - 340 MB | NPU
113
- | VIT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.919 ms | 1 - 156 MB | NPU
114
- | VIT | QNN_DLC | float | Snapdragon® X2 Elite | 3.522 ms | 1 - 1 MB | NPU
115
- | VIT | QNN_DLC | float | Snapdragon® X Elite | 8.311 ms | 1 - 1 MB | NPU
116
- | VIT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.402 ms | 0 - 249 MB | NPU
117
- | VIT | QNN_DLC | float | Qualcomm® QCS8275 | 34.803 ms | 1 - 168 MB | NPU
118
- | VIT | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 7.711 ms | 1 - 3 MB | NPU
119
- | VIT | QNN_DLC | float | Qualcomm® SA8775P | 10.485 ms | 1 - 168 MB | NPU
120
- | VIT | QNN_DLC | float | Qualcomm® SA8650P | 10.485 ms | 1 - 168 MB | NPU
121
- | VIT | QNN_DLC | float | Qualcomm® SA8255P | 10.485 ms | 1 - 168 MB | NPU
122
- | VIT | QNN_DLC | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.744 ms | 0 - 155 MB | NPU
123
- | VIT | QNN_DLC | float | Qualcomm® QCS8450 (Proxy) | 13.028 ms | 0 - 228 MB | NPU
124
- | VIT | QNN_DLC | float | Qualcomm® SA7255P | 34.803 ms | 1 - 168 MB | NPU
125
- | VIT | QNN_DLC | float | Qualcomm® QCS9075 | 10.64 ms | 3 - 5 MB | NPU
126
  | VIT | QNN_DLC | float | Qualcomm® SA8295P | 12.955 ms | 1 - 145 MB | NPU
127
- | VIT | QNN_DLC | float | Qualcomm® QCS8750 | 3.744 ms | 0 - 155 MB | NPU
128
- | VIT | QNN_DLC | float | Qualcomm® QCS7181 | 8.311 ms | 1 - 1 MB | NPU
129
- | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.83 ms | 0 - 276 MB | NPU
130
- | VIT | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 3.582 ms | 0 - 0 MB | NPU
131
- | VIT | QNN_DLC | w8a16 | Snapdragon® X Elite | 8.281 ms | 0 - 0 MB | NPU
132
- | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.079 ms | 0 - 320 MB | NPU
 
133
  | VIT | QNN_DLC | w8a16 | Qualcomm® QCS8275 | 17.354 ms | 0 - 258 MB | NPU
134
- | VIT | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 7.654 ms | 0 - 2 MB | NPU
135
- | VIT | QNN_DLC | w8a16 | Qualcomm® SA8775P | 7.768 ms | 0 - 259 MB | NPU
136
- | VIT | QNN_DLC | w8a16 | Qualcomm® SA8650P | 7.768 ms | 0 - 259 MB | NPU
137
- | VIT | QNN_DLC | w8a16 | Qualcomm® SA8255P | 7.768 ms | 0 - 259 MB | NPU
138
- | VIT | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 13.167 ms | 0 - 403 MB | NPU
139
- | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Elite For Galaxy Mobile | 3.903 ms | 0 - 260 MB | NPU
140
- | VIT | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 119.493 ms | 0 - 404 MB | NPU
141
  | VIT | QNN_DLC | w8a16 | Qualcomm® SA7255P | 17.354 ms | 0 - 258 MB | NPU
142
- | VIT | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 7.949 ms | 2 - 4 MB | NPU
143
- | VIT | QNN_DLC | w8a16 | Qualcomm® QCS7790 | 13.167 ms | 0 - 403 MB | NPU
144
- | VIT | QNN_DLC | w8a16 | Qualcomm® QCS8750 | 3.903 ms | 0 - 260 MB | NPU
145
- | VIT | QNN_DLC | w8a16 | Qualcomm® QCS7181 | 8.281 ms | 0 - 0 MB | NPU
146
- | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.493 ms | 0 - 209 MB | NPU
147
  | VIT | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 4.472 ms | 0 - 0 MB | NPU
148
- | VIT | QNN_DLC | w8a8 | Snapdragon® X Elite | 10.247 ms | 0 - 0 MB | NPU
149
- | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 6.51 ms | 0 - 306 MB | NPU
150
- | VIT | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 50.478 ms | 0 - 2 MB | NPU
151
- | VIT | QNN_DLC | w8a8 | Qualcomm® QCS8275 | 28.499 ms | 0 - 202 MB | NPU
152
- | VIT | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 9.598 ms | 0 - 7 MB | NPU
153
- | VIT | QNN_DLC | w8a8 | Qualcomm® SA8775P | 8.655 ms | 0 - 202 MB | NPU
154
- | VIT | QNN_DLC | w8a8 | Qualcomm® SA8650P | 8.655 ms | 0 - 202 MB | NPU
155
- | VIT | QNN_DLC | w8a8 | Qualcomm® SA8255P | 8.655 ms | 0 - 202 MB | NPU
156
- | VIT | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 9.409 ms | 0 - 2 MB | NPU
157
- | VIT | QNN_DLC | w8a8 | Qualcomm® QCS8450 (Proxy) | 12.938 ms | 0 - 311 MB | NPU
158
- | VIT | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 19.767 ms | 0 - 355 MB | NPU
159
- | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 5.438 ms | 0 - 203 MB | NPU
160
- | VIT | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 221.972 ms | 2 - 498 MB | NPU
161
- | VIT | QNN_DLC | w8a8 | Qualcomm® SA8295P | 15.579 ms | 0 - 212 MB | NPU
162
- | VIT | QNN_DLC | w8a8 | Qualcomm® SA7255P | 28.499 ms | 0 - 202 MB | NPU
163
- | VIT | QNN_DLC | w8a8 | Qualcomm® QCS7790 | 19.767 ms | 0 - 355 MB | NPU
164
- | VIT | QNN_DLC | w8a8 | Qualcomm® QCS8750 | 5.438 ms | 0 - 203 MB | NPU
165
- | VIT | QNN_DLC | w8a8 | Qualcomm® QCS7181 | 10.247 ms | 0 - 0 MB | NPU
166
- | VIT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.029 ms | 0 - 169 MB | NPU
167
- | VIT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.285 ms | 0 - 311 MB | NPU
168
- | VIT | TFLITE | float | Qualcomm® QCS8275 | 34.603 ms | 0 - 168 MB | NPU
169
- | VIT | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 7.235 ms | 0 - 3 MB | NPU
170
- | VIT | TFLITE | float | Qualcomm® SA8775P | 10.172 ms | 0 - 184 MB | NPU
171
- | VIT | TFLITE | float | Qualcomm® SA8650P | 10.172 ms | 0 - 184 MB | NPU
172
- | VIT | TFLITE | float | Qualcomm® SA8255P | 10.172 ms | 0 - 184 MB | NPU
173
- | VIT | TFLITE | float | Snapdragon® 8 Elite For Galaxy Mobile | 3.684 ms | 0 - 176 MB | NPU
174
- | VIT | TFLITE | float | Qualcomm® QCS8450 (Proxy) | 12.977 ms | 0 - 291 MB | NPU
175
- | VIT | TFLITE | float | Qualcomm® SA7255P | 34.603 ms | 0 - 168 MB | NPU
176
- | VIT | TFLITE | float | Qualcomm® QCS9075 | 10.819 ms | 0 - 173 MB | NPU
177
- | VIT | TFLITE | float | Qualcomm® SA8295P | 13.28 ms | 0 - 156 MB | NPU
178
- | VIT | TFLITE | float | Qualcomm® QCS8750 | 3.684 ms | 0 - 176 MB | NPU
179
- | VIT | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 4.536 ms | 0 - 379 MB | NPU
180
- | VIT | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 8.66 ms | 0 - 486 MB | NPU
181
- | VIT | TFLITE | w8a8 | Qualcomm® QCS6490 | 133.07 ms | 1 - 100 MB | NPU
182
- | VIT | TFLITE | w8a8 | Qualcomm® QCS8275 | 35.05 ms | 0 - 385 MB | NPU
183
- | VIT | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 12.383 ms | 0 - 3 MB | NPU
184
- | VIT | TFLITE | w8a8 | Qualcomm® SA8775P | 12.217 ms | 0 - 388 MB | NPU
185
- | VIT | TFLITE | w8a8 | Qualcomm® SA8650P | 12.217 ms | 0 - 388 MB | NPU
186
- | VIT | TFLITE | w8a8 | Qualcomm® SA8255P | 12.217 ms | 0 - 388 MB | NPU
187
- | VIT | TFLITE | w8a8 | Qualcomm® QCS9075 | 13.795 ms | 0 - 88 MB | NPU
188
- | VIT | TFLITE | w8a8 | Qualcomm® QCS8450 (Proxy) | 20.321 ms | 0 - 448 MB | NPU
189
- | VIT | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 29.571 ms | 1 - 214 MB | NPU
190
- | VIT | TFLITE | w8a8 | Snapdragon® 8 Elite For Galaxy Mobile | 6.972 ms | 0 - 380 MB | NPU
191
- | VIT | TFLITE | w8a8 | Qualcomm® QCM6690 | 202.521 ms | 2 - 282 MB | NPU
192
- | VIT | TFLITE | w8a8 | Qualcomm® SA8295P | 19.243 ms | 0 - 345 MB | NPU
193
- | VIT | TFLITE | w8a8 | Qualcomm® SA7255P | 35.05 ms | 0 - 385 MB | NPU
194
- | VIT | TFLITE | w8a8 | Qualcomm® QCS7790 | 29.571 ms | 1 - 214 MB | NPU
195
- | VIT | TFLITE | w8a8 | Qualcomm® QCS8750 | 6.972 ms | 0 - 380 MB | NPU
 
196
 
197
  ## License
198
  * 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 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.56.0/vit-onnx-float.zip)
32
+ | ONNX | w8a16 | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.56.0/vit-onnx-w8a16.zip)
33
+ | ONNX | w8a8 | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.56.0/vit-onnx-w8a8.zip)
34
+ | ONNX | w8a8_mixed_int16 | Universal | QAIRT 2.45, ONNX Runtime 1.25.0 | [Download](https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.56.0/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/v0.56.0/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/v0.56.0/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/v0.56.0/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/v0.56.0/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/v0.56.0/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® X2 Elite | 3.055 ms | 181 - 181 MB | NPU
71
+ | VIT | ONNX | float | Snapdragon® X Elite | 7.504 ms | 170 - 170 MB | NPU
72
+ | VIT | ONNX | float | Snapdragon® 8 Gen 3 Mobile | 5.023 ms | 1 - 295 MB | NPU
73
+ | VIT | ONNX | float | Snapdragon® 8 Gen 1 Mobile | 12.142 ms | 1 - 272 MB | NPU
74
+ | VIT | ONNX | float | Qualcomm® QCS8550 (Proxy) | 7.193 ms | 1 - 5 MB | NPU
75
+ | VIT | ONNX | float | Qualcomm® QCS8450 | 12.142 ms | 1 - 272 MB | NPU
76
+ | VIT | ONNX | float | Snapdragon® 8 Elite Mobile | 3.489 ms | 0 - 175 MB | NPU
77
+ | VIT | ONNX | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.801 ms | 1 - 159 MB | NPU
78
+ | VIT | ONNX | float | Qualcomm® QCS9075 | 10.188 ms | 1 - 46 MB | NPU
79
+ | VIT | ONNX | float | Qualcomm® QCS8750 | 3.489 ms | 0 - 175 MB | NPU
80
+ | VIT | ONNX | float | Qualcomm® QCS7181 | 7.504 ms | 170 - 170 MB | NPU
81
+ | VIT | ONNX | w8a16 | Snapdragon® X2 Elite | 2.01 ms | 183 - 183 MB | NPU
82
+ | VIT | ONNX | w8a16 | Snapdragon® X Elite | 4.749 ms | 150 - 150 MB | NPU
83
+ | VIT | ONNX | w8a16 | Snapdragon® 8 Gen 3 Mobile | 3.108 ms | 0 - 304 MB | NPU
84
+ | VIT | ONNX | w8a16 | Qualcomm® QCS8550 (Proxy) | 4.621 ms | 0 - 4 MB | NPU
85
+ | VIT | ONNX | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 1.773 ms | 0 - 266 MB | NPU
86
+ | VIT | ONNX | w8a16 | Snapdragon® 8 Elite Mobile | 2.426 ms | 0 - 260 MB | NPU
87
+ | VIT | ONNX | w8a16 | Qualcomm® QCS9075 | 4.718 ms | 0 - 45 MB | NPU
88
+ | VIT | ONNX | w8a16 | Snapdragon® 7 Gen 4 Mobile | 5.892 ms | 0 - 393 MB | NPU
89
+ | VIT | ONNX | w8a16 | Qualcomm® QCM6690 | 50.539 ms | 0 - 401 MB | NPU
90
+ | VIT | ONNX | w8a16 | Qualcomm® QCS7790 | 5.892 ms | 0 - 393 MB | NPU
91
+ | VIT | ONNX | w8a16 | Qualcomm® QCS8750 | 2.426 ms | 0 - 260 MB | NPU
92
+ | VIT | ONNX | w8a16 | Qualcomm® QCS7181 | 4.749 ms | 150 - 150 MB | NPU
93
+ | VIT | ONNX | w8a8 | Snapdragon® X2 Elite | 4.117 ms | 212 - 212 MB | NPU
94
+ | VIT | ONNX | w8a8 | Snapdragon® X Elite | 9.751 ms | 181 - 181 MB | NPU
95
+ | VIT | ONNX | w8a8 | Snapdragon® 8 Gen 3 Mobile | 6.321 ms | 0 - 323 MB | NPU
96
+ | VIT | ONNX | w8a8 | Snapdragon® 8 Gen 1 Mobile | 13.243 ms | 0 - 330 MB | NPU
97
+ | VIT | ONNX | w8a8 | Qualcomm® QCS6490 | 50.336 ms | 0 - 45 MB | NPU
98
+ | VIT | ONNX | w8a8 | Qualcomm® QCS8550 (Proxy) | 9.369 ms | 0 - 100 MB | NPU
99
+ | VIT | ONNX | w8a8 | Qualcomm® QCS8450 | 13.243 ms | 0 - 330 MB | NPU
100
+ | VIT | ONNX | w8a8 | Qualcomm® QCS9075 | 9.243 ms | 0 - 45 MB | NPU
101
+ | VIT | ONNX | w8a8 | Qualcomm® QCM6690 | 186.722 ms | 0 - 523 MB | NPU
102
+ | VIT | ONNX | w8a8 | Snapdragon® 7 Gen 4 Mobile | 17.073 ms | 0 - 390 MB | NPU
103
+ | VIT | ONNX | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.463 ms | 0 - 242 MB | NPU
104
+ | VIT | ONNX | w8a8 | Snapdragon® 8 Elite Mobile | 5.456 ms | 0 - 239 MB | NPU
105
+ | VIT | ONNX | w8a8 | Qualcomm® QCS7790 | 17.073 ms | 0 - 390 MB | NPU
106
+ | VIT | ONNX | w8a8 | Qualcomm® QCS8750 | 5.456 ms | 0 - 239 MB | NPU
107
+ | VIT | ONNX | w8a8 | Qualcomm® QCS7181 | 9.751 ms | 181 - 181 MB | NPU
108
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Gen 3 Mobile | 70.212 ms | 59 - 410 MB | NPU
109
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite Mobile | 56.595 ms | 61 - 327 MB | NPU
110
+ | VIT | ONNX | w8a8_mixed_int16 | Snapdragon® 8 Elite Gen 5 Mobile | 48.199 ms | 60 - 333 MB | NPU
111
+ | VIT | ONNX | w8a8_mixed_int16 | Qualcomm® QCS8750 | 56.595 ms | 61 - 327 MB | NPU
112
+ | VIT | QNN_DLC | float | Snapdragon® X2 Elite | 3.52 ms | 1 - 1 MB | NPU
113
+ | VIT | QNN_DLC | float | Snapdragon® X Elite | 8.3 ms | 1 - 1 MB | NPU
114
+ | VIT | QNN_DLC | float | Snapdragon® 8 Gen 3 Mobile | 5.393 ms | 0 - 251 MB | NPU
115
+ | VIT | QNN_DLC | float | Snapdragon® 8 Gen 1 Mobile | 13.078 ms | 1 - 229 MB | NPU
116
+ | VIT | QNN_DLC | float | Qualcomm® QCS8275 | 34.807 ms | 1 - 168 MB | NPU
117
+ | VIT | QNN_DLC | float | Qualcomm® QCS8550 (Proxy) | 7.715 ms | 1 - 400 MB | NPU
118
+ | VIT | QNN_DLC | float | Qualcomm® QCS8450 | 13.078 ms | 1 - 229 MB | NPU
119
+ | VIT | QNN_DLC | float | Snapdragon® 8 Elite Mobile | 3.754 ms | 0 - 155 MB | NPU
120
+ | VIT | QNN_DLC | float | Qualcomm® SA7255P | 34.807 ms | 1 - 168 MB | NPU
 
 
 
 
 
121
  | VIT | QNN_DLC | float | Qualcomm® SA8295P | 12.955 ms | 1 - 145 MB | NPU
122
+ | VIT | QNN_DLC | float | Snapdragon® 8 Elite Gen 5 Mobile | 2.931 ms | 1 - 157 MB | NPU
123
+ | VIT | QNN_DLC | float | Qualcomm® QCS9075 | 10.721 ms | 1 - 3 MB | NPU
124
+ | VIT | QNN_DLC | float | Qualcomm® QCS8750 | 3.754 ms | 0 - 155 MB | NPU
125
+ | VIT | QNN_DLC | float | Qualcomm® QCS7181 | 8.3 ms | 1 - 1 MB | NPU
126
+ | VIT | QNN_DLC | w8a16 | Snapdragon® X2 Elite | 3.585 ms | 0 - 0 MB | NPU
127
+ | VIT | QNN_DLC | w8a16 | Snapdragon® X Elite | 8.26 ms | 0 - 0 MB | NPU
128
+ | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Gen 3 Mobile | 5.088 ms | 0 - 321 MB | NPU
129
  | VIT | QNN_DLC | w8a16 | Qualcomm® QCS8275 | 17.354 ms | 0 - 258 MB | NPU
130
+ | VIT | QNN_DLC | w8a16 | Qualcomm® QCS8550 (Proxy) | 7.642 ms | 0 - 35 MB | NPU
131
+ | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Elite Gen 5 Mobile | 2.85 ms | 0 - 277 MB | NPU
132
+ | VIT | QNN_DLC | w8a16 | Snapdragon® 8 Elite Mobile | 3.887 ms | 0 - 260 MB | NPU
133
+ | VIT | QNN_DLC | w8a16 | Qualcomm® QCS9075 | 7.974 ms | 0 - 2 MB | NPU
134
+ | VIT | QNN_DLC | w8a16 | Snapdragon® 7 Gen 4 Mobile | 12.979 ms | 0 - 402 MB | NPU
135
+ | VIT | QNN_DLC | w8a16 | Qualcomm® QCM6690 | 120.068 ms | 0 - 401 MB | NPU
 
136
  | VIT | QNN_DLC | w8a16 | Qualcomm® SA7255P | 17.354 ms | 0 - 258 MB | NPU
137
+ | VIT | QNN_DLC | w8a16 | Qualcomm® QCS7790 | 12.979 ms | 0 - 402 MB | NPU
138
+ | VIT | QNN_DLC | w8a16 | Qualcomm® QCS8750 | 3.887 ms | 0 - 260 MB | NPU
139
+ | VIT | QNN_DLC | w8a16 | Qualcomm® QCS7181 | 8.26 ms | 0 - 0 MB | NPU
 
 
140
  | VIT | QNN_DLC | w8a8 | Snapdragon® X2 Elite | 4.472 ms | 0 - 0 MB | NPU
141
+ | VIT | QNN_DLC | w8a8 | Snapdragon® X Elite | 10.216 ms | 0 - 0 MB | NPU
142
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Gen 3 Mobile | 6.449 ms | 0 - 305 MB | NPU
143
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Gen 1 Mobile | 13.271 ms | 0 - 312 MB | NPU
144
+ | VIT | QNN_DLC | w8a8 | Qualcomm® QCS6490 | 50.709 ms | 0 - 2 MB | NPU
145
+ | VIT | QNN_DLC | w8a8 | Qualcomm® QCS8275 | 28.517 ms | 0 - 201 MB | NPU
146
+ | VIT | QNN_DLC | w8a8 | Qualcomm® QCS8550 (Proxy) | 9.585 ms | 0 - 118 MB | NPU
147
+ | VIT | QNN_DLC | w8a8 | Qualcomm® QCS8450 | 13.271 ms | 0 - 312 MB | NPU
148
+ | VIT | QNN_DLC | w8a8 | Qualcomm® QCS9075 | 9.413 ms | 0 - 2 MB | NPU
149
+ | VIT | QNN_DLC | w8a8 | Qualcomm® SA7255P | 28.517 ms | 0 - 201 MB | NPU
150
+ | VIT | QNN_DLC | w8a8 | Qualcomm® QCM6690 | 188.78 ms | 0 - 501 MB | NPU
151
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 7 Gen 4 Mobile | 19.356 ms | 0 - 358 MB | NPU
152
+ | VIT | QNN_DLC | w8a8 | Qualcomm® SA8295P | 15.62 ms | 0 - 212 MB | NPU
153
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 3.498 ms | 0 - 209 MB | NPU
154
+ | VIT | QNN_DLC | w8a8 | Snapdragon® 8 Elite Mobile | 5.377 ms | 0 - 204 MB | NPU
155
+ | VIT | QNN_DLC | w8a8 | Qualcomm® QCS7790 | 19.356 ms | 0 - 358 MB | NPU
156
+ | VIT | QNN_DLC | w8a8 | Qualcomm® QCS8750 | 5.377 ms | 0 - 204 MB | NPU
157
+ | VIT | QNN_DLC | w8a8 | Qualcomm® QCS7181 | 10.216 ms | 0 - 0 MB | NPU
158
+ | VIT | TFLITE | float | Snapdragon® 8 Gen 3 Mobile | 5.267 ms | 0 - 306 MB | NPU
159
+ | VIT | TFLITE | float | Snapdragon® 8 Gen 1 Mobile | 12.961 ms | 0 - 290 MB | NPU
160
+ | VIT | TFLITE | float | Qualcomm® QCS8275 | 34.607 ms | 0 - 169 MB | NPU
161
+ | VIT | TFLITE | float | Qualcomm® QCS8550 (Proxy) | 7.258 ms | 0 - 5 MB | NPU
162
+ | VIT | TFLITE | float | Qualcomm® SA8775P | 281.845 ms | 3 - 47 MB | CPU
163
+ | VIT | TFLITE | float | Qualcomm® SA8650P | 281.845 ms | 3 - 47 MB | CPU
164
+ | VIT | TFLITE | float | Qualcomm® SA8255P | 281.845 ms | 3 - 47 MB | CPU
165
+ | VIT | TFLITE | float | Qualcomm® QCS8450 | 12.961 ms | 0 - 290 MB | NPU
166
+ | VIT | TFLITE | float | Snapdragon® 8 Elite Mobile | 3.656 ms | 0 - 177 MB | NPU
167
+ | VIT | TFLITE | float | Qualcomm® SA7255P | 34.607 ms | 0 - 169 MB | NPU
168
+ | VIT | TFLITE | float | Qualcomm® SA8295P | 13.301 ms | 0 - 157 MB | NPU
169
+ | VIT | TFLITE | float | Snapdragon® 8 Elite Gen 5 Mobile | 3.032 ms | 0 - 171 MB | NPU
170
+ | VIT | TFLITE | float | Qualcomm® QCS9075 | 10.619 ms | 0 - 173 MB | NPU
171
+ | VIT | TFLITE | float | Qualcomm® QCS8750 | 3.656 ms | 0 - 177 MB | NPU
172
+ | VIT | TFLITE | w8a8 | Snapdragon® 8 Gen 3 Mobile | 8.688 ms | 0 - 487 MB | NPU
173
+ | VIT | TFLITE | w8a8 | Snapdragon® 8 Gen 1 Mobile | 21.745 ms | 0 - 449 MB | NPU
174
+ | VIT | TFLITE | w8a8 | Qualcomm® QCS6490 | 144.275 ms | 1 - 100 MB | NPU
175
+ | VIT | TFLITE | w8a8 | Qualcomm® QCS8275 | 35.047 ms | 0 - 385 MB | NPU
176
+ | VIT | TFLITE | w8a8 | Qualcomm® QCS8550 (Proxy) | 12.343 ms | 0 - 3 MB | NPU
177
+ | VIT | TFLITE | w8a8 | Qualcomm® SA8775P | 99.096 ms | 0 - 52 MB | CPU
178
+ | VIT | TFLITE | w8a8 | Qualcomm® SA8650P | 99.096 ms | 0 - 52 MB | CPU
179
+ | VIT | TFLITE | w8a8 | Qualcomm® SA8255P | 99.096 ms | 0 - 52 MB | CPU
180
+ | VIT | TFLITE | w8a8 | Qualcomm® QCS8450 | 21.745 ms | 0 - 449 MB | NPU
181
+ | VIT | TFLITE | w8a8 | Qualcomm® QCS9075 | 13.592 ms | 0 - 88 MB | NPU
182
+ | VIT | TFLITE | w8a8 | Qualcomm® SA7255P | 35.047 ms | 0 - 385 MB | NPU
183
+ | VIT | TFLITE | w8a8 | Qualcomm® QCM6690 | 201.234 ms | 1 - 283 MB | NPU
184
+ | VIT | TFLITE | w8a8 | Snapdragon® 7 Gen 4 Mobile | 29.823 ms | 1 - 215 MB | NPU
185
+ | VIT | TFLITE | w8a8 | Qualcomm® SA8295P | 19.253 ms | 0 - 346 MB | NPU
186
+ | VIT | TFLITE | w8a8 | Snapdragon® 8 Elite Gen 5 Mobile | 4.553 ms | 0 - 383 MB | NPU
187
+ | VIT | TFLITE | w8a8 | Snapdragon® 8 Elite Mobile | 6.924 ms | 0 - 380 MB | NPU
188
+ | VIT | TFLITE | w8a8 | Qualcomm® QCS7790 | 29.823 ms | 1 - 215 MB | NPU
189
+ | VIT | TFLITE | w8a8 | Qualcomm® QCS8750 | 6.924 ms | 0 - 380 MB | NPU
190
 
191
  ## License
192
  * The license for the original implementation of VIT can be found
release_assets.json CHANGED
@@ -1,79 +1,79 @@
1
  {
2
- "version": "0.55.0",
3
  "precisions": {
4
- "w8a16": {
5
  "universal_assets": {
 
 
 
 
 
 
 
6
  "qnn_dlc": {
7
  "tool_versions": {
8
  "qairt": "2.45.0.260326154327"
9
  },
10
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.55.0/vit-qnn_dlc-w8a16.zip"
11
  },
12
  "onnx": {
13
  "tool_versions": {
14
- "qairt": "2.42.0.251225135753_193295",
15
  "onnx_runtime": "1.25.0"
16
  },
17
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.55.0/vit-onnx-w8a16.zip"
18
  }
19
  }
20
  },
21
- "float": {
22
  "universal_assets": {
23
- "tflite": {
24
- "tool_versions": {
25
- "qairt": "2.45.0.260326154327",
26
- "litert": "1.4.3"
27
- },
28
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.55.0/vit-tflite-float.zip"
29
- },
30
  "qnn_dlc": {
31
  "tool_versions": {
32
  "qairt": "2.45.0.260326154327"
33
  },
34
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.55.0/vit-qnn_dlc-float.zip"
35
  },
36
  "onnx": {
37
  "tool_versions": {
38
- "qairt": "2.42.0.251225135753_193295",
39
  "onnx_runtime": "1.25.0"
40
  },
41
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.55.0/vit-onnx-float.zip"
42
  }
43
  }
44
  },
45
- "w8a8": {
 
 
 
 
 
 
 
 
 
 
 
46
  "universal_assets": {
47
  "tflite": {
48
  "tool_versions": {
49
  "qairt": "2.45.0.260326154327",
50
- "litert": "1.4.3"
51
  },
52
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.55.0/vit-tflite-w8a8.zip"
53
  },
54
  "qnn_dlc": {
55
  "tool_versions": {
56
  "qairt": "2.45.0.260326154327"
57
  },
58
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.55.0/vit-qnn_dlc-w8a8.zip"
59
  },
60
  "onnx": {
61
  "tool_versions": {
62
- "qairt": "2.42.0.251225135753_193295",
63
- "onnx_runtime": "1.25.0"
64
- },
65
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.55.0/vit-onnx-w8a8.zip"
66
- }
67
- }
68
- },
69
- "w8a8_mixed_int16": {
70
- "universal_assets": {
71
- "onnx": {
72
- "tool_versions": {
73
- "qairt": "2.42.0.251225135753_193295",
74
  "onnx_runtime": "1.25.0"
75
  },
76
- "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.55.0/vit-onnx-w8a8_mixed_int16.zip"
77
  }
78
  }
79
  }
 
1
  {
2
+ "version": "0.56.0",
3
  "precisions": {
4
+ "w8a8": {
5
  "universal_assets": {
6
+ "tflite": {
7
+ "tool_versions": {
8
+ "qairt": "2.45.0.260326154327",
9
+ "litert": "1.4.4"
10
+ },
11
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.56.0/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/v0.56.0/vit-qnn_dlc-w8a8.zip"
18
  },
19
  "onnx": {
20
  "tool_versions": {
21
+ "qairt": "2.45.0.260326154327",
22
  "onnx_runtime": "1.25.0"
23
  },
24
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.56.0/vit-onnx-w8a8.zip"
25
  }
26
  }
27
  },
28
+ "w8a16": {
29
  "universal_assets": {
 
 
 
 
 
 
 
30
  "qnn_dlc": {
31
  "tool_versions": {
32
  "qairt": "2.45.0.260326154327"
33
  },
34
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.56.0/vit-qnn_dlc-w8a16.zip"
35
  },
36
  "onnx": {
37
  "tool_versions": {
38
+ "qairt": "2.45.0.260326154327",
39
  "onnx_runtime": "1.25.0"
40
  },
41
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.56.0/vit-onnx-w8a16.zip"
42
  }
43
  }
44
  },
45
+ "w8a8_mixed_int16": {
46
+ "universal_assets": {
47
+ "onnx": {
48
+ "tool_versions": {
49
+ "qairt": "2.45.0.260326154327",
50
+ "onnx_runtime": "1.25.0"
51
+ },
52
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.56.0/vit-onnx-w8a8_mixed_int16.zip"
53
+ }
54
+ }
55
+ },
56
+ "float": {
57
  "universal_assets": {
58
  "tflite": {
59
  "tool_versions": {
60
  "qairt": "2.45.0.260326154327",
61
+ "litert": "1.4.4"
62
  },
63
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.56.0/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/v0.56.0/vit-qnn_dlc-float.zip"
70
  },
71
  "onnx": {
72
  "tool_versions": {
73
+ "qairt": "2.45.0.260326154327",
 
 
 
 
 
 
 
 
 
 
 
74
  "onnx_runtime": "1.25.0"
75
  },
76
+ "download_url": "https://qaihub-public-assets.s3.us-west-2.amazonaws.com/qai-hub-models/models/vit/releases/v0.56.0/vit-onnx-float.zip"
77
  }
78
  }
79
  }