Upload README.md with huggingface_hub
Browse files
README.md
CHANGED
|
@@ -37,39 +37,39 @@ More details on model performance across various devices, can be found
|
|
| 37 |
|
| 38 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
| 39 |
|---|---|---|---|---|---|---|---|---|
|
| 40 |
-
| TextEncoderQuantizable | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 6.
|
| 41 |
-
| TextEncoderQuantizable | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 4.
|
| 42 |
-
| TextEncoderQuantizable | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 4.
|
| 43 |
-
| TextEncoderQuantizable | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 6.
|
| 44 |
-
| TextEncoderQuantizable | SA7255P ADP | SA7255P | QNN | 88.
|
| 45 |
-
| TextEncoderQuantizable | SA8255 (Proxy) | SA8255P Proxy | QNN | 6.
|
| 46 |
-
| TextEncoderQuantizable | SA8650 (Proxy) | SA8650P Proxy | QNN | 6.
|
| 47 |
-
| TextEncoderQuantizable | SA8775P ADP | SA8775P | QNN | 7.
|
| 48 |
-
| TextEncoderQuantizable | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 88.
|
| 49 |
-
| TextEncoderQuantizable | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 6.
|
| 50 |
-
| TextEncoderQuantizable | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 7.
|
| 51 |
-
| UnetQuantizable | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN |
|
| 52 |
-
| UnetQuantizable | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 69.
|
| 53 |
-
| UnetQuantizable | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 61.
|
| 54 |
-
| UnetQuantizable | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 99.
|
| 55 |
-
| UnetQuantizable | SA7255P ADP | SA7255P | QNN |
|
| 56 |
-
| UnetQuantizable | SA8255 (Proxy) | SA8255P Proxy | QNN |
|
| 57 |
-
| UnetQuantizable | SA8650 (Proxy) | SA8650P Proxy | QNN | 97.
|
| 58 |
-
| UnetQuantizable | SA8775P ADP | SA8775P | QNN | 110.
|
| 59 |
-
| UnetQuantizable | QCS8275 (Proxy) | QCS8275 Proxy | QNN |
|
| 60 |
-
| UnetQuantizable | QCS8550 (Proxy) | QCS8550 Proxy | QNN |
|
| 61 |
-
| UnetQuantizable | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 110.
|
| 62 |
-
| VaeDecoderQuantizable | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN |
|
| 63 |
-
| VaeDecoderQuantizable | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN |
|
| 64 |
-
| VaeDecoderQuantizable | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 189.
|
| 65 |
-
| VaeDecoderQuantizable | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN |
|
| 66 |
-
| VaeDecoderQuantizable | SA7255P ADP | SA7255P | QNN |
|
| 67 |
-
| VaeDecoderQuantizable | SA8255 (Proxy) | SA8255P Proxy | QNN | 274.
|
| 68 |
-
| VaeDecoderQuantizable | SA8650 (Proxy) | SA8650P Proxy | QNN |
|
| 69 |
-
| VaeDecoderQuantizable | SA8775P ADP | SA8775P | QNN | 301.
|
| 70 |
-
| VaeDecoderQuantizable | QCS8275 (Proxy) | QCS8275 Proxy | QNN |
|
| 71 |
-
| VaeDecoderQuantizable | QCS8550 (Proxy) | QCS8550 Proxy | QNN |
|
| 72 |
-
| VaeDecoderQuantizable | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 301.
|
| 73 |
|
| 74 |
|
| 75 |
|
|
@@ -133,8 +133,8 @@ Profiling Results
|
|
| 133 |
TextEncoderQuantizable
|
| 134 |
Device : Samsung Galaxy S23 (13)
|
| 135 |
Runtime : QNN
|
| 136 |
-
Estimated inference time (ms) : 6.
|
| 137 |
-
Estimated peak memory usage (MB): [0,
|
| 138 |
Total # Ops : 787
|
| 139 |
Compute Unit(s) : NPU (787 ops)
|
| 140 |
|
|
@@ -142,7 +142,7 @@ Compute Unit(s) : NPU (787 ops)
|
|
| 142 |
UnetQuantizable
|
| 143 |
Device : Samsung Galaxy S23 (13)
|
| 144 |
Runtime : QNN
|
| 145 |
-
Estimated inference time (ms) : 97.
|
| 146 |
Estimated peak memory usage (MB): [0, 3]
|
| 147 |
Total # Ops : 5891
|
| 148 |
Compute Unit(s) : NPU (5891 ops)
|
|
@@ -151,8 +151,8 @@ Compute Unit(s) : NPU (5891 ops)
|
|
| 151 |
VaeDecoderQuantizable
|
| 152 |
Device : Samsung Galaxy S23 (13)
|
| 153 |
Runtime : QNN
|
| 154 |
-
Estimated inference time (ms) :
|
| 155 |
-
Estimated peak memory usage (MB): [0,
|
| 156 |
Total # Ops : 189
|
| 157 |
Compute Unit(s) : NPU (189 ops)
|
| 158 |
```
|
|
|
|
| 37 |
|
| 38 |
| Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
|
| 39 |
|---|---|---|---|---|---|---|---|---|
|
| 40 |
+
| TextEncoderQuantizable | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 6.666 ms | 0 - 3 MB | W8A16 | NPU | [Stable-Diffusion-v2.1.so](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/TextEncoderQuantizable.so) |
|
| 41 |
+
| TextEncoderQuantizable | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 4.647 ms | 0 - 20 MB | W8A16 | NPU | [Stable-Diffusion-v2.1.so](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/TextEncoderQuantizable.so) |
|
| 42 |
+
| TextEncoderQuantizable | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 4.2 ms | 0 - 15 MB | W8A16 | NPU | Use Export Script |
|
| 43 |
+
| TextEncoderQuantizable | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 6.84 ms | 0 - 0 MB | W8A16 | NPU | Use Export Script |
|
| 44 |
+
| TextEncoderQuantizable | SA7255P ADP | SA7255P | QNN | 88.113 ms | 0 - 9 MB | W8A16 | NPU | Use Export Script |
|
| 45 |
+
| TextEncoderQuantizable | SA8255 (Proxy) | SA8255P Proxy | QNN | 6.62 ms | 0 - 3 MB | W8A16 | NPU | Use Export Script |
|
| 46 |
+
| TextEncoderQuantizable | SA8650 (Proxy) | SA8650P Proxy | QNN | 6.654 ms | 0 - 2 MB | W8A16 | NPU | Use Export Script |
|
| 47 |
+
| TextEncoderQuantizable | SA8775P ADP | SA8775P | QNN | 7.869 ms | 0 - 10 MB | W8A16 | NPU | Use Export Script |
|
| 48 |
+
| TextEncoderQuantizable | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 88.113 ms | 0 - 9 MB | W8A16 | NPU | Use Export Script |
|
| 49 |
+
| TextEncoderQuantizable | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 6.636 ms | 0 - 3 MB | W8A16 | NPU | Use Export Script |
|
| 50 |
+
| TextEncoderQuantizable | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 7.869 ms | 0 - 10 MB | W8A16 | NPU | Use Export Script |
|
| 51 |
+
| UnetQuantizable | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 96.977 ms | 0 - 3 MB | W8A16 | NPU | [Stable-Diffusion-v2.1.so](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/UnetQuantizable.so) |
|
| 52 |
+
| UnetQuantizable | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 69.178 ms | 0 - 17 MB | W8A16 | NPU | [Stable-Diffusion-v2.1.so](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/UnetQuantizable.so) |
|
| 53 |
+
| UnetQuantizable | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 61.668 ms | 0 - 14 MB | W8A16 | NPU | Use Export Script |
|
| 54 |
+
| UnetQuantizable | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 99.461 ms | 0 - 0 MB | W8A16 | NPU | Use Export Script |
|
| 55 |
+
| UnetQuantizable | SA7255P ADP | SA7255P | QNN | 1467.935 ms | 0 - 7 MB | W8A16 | NPU | Use Export Script |
|
| 56 |
+
| UnetQuantizable | SA8255 (Proxy) | SA8255P Proxy | QNN | 98.746 ms | 0 - 2 MB | W8A16 | NPU | Use Export Script |
|
| 57 |
+
| UnetQuantizable | SA8650 (Proxy) | SA8650P Proxy | QNN | 97.177 ms | 1 - 3 MB | W8A16 | NPU | Use Export Script |
|
| 58 |
+
| UnetQuantizable | SA8775P ADP | SA8775P | QNN | 110.665 ms | 0 - 8 MB | W8A16 | NPU | Use Export Script |
|
| 59 |
+
| UnetQuantizable | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 1467.935 ms | 0 - 7 MB | W8A16 | NPU | Use Export Script |
|
| 60 |
+
| UnetQuantizable | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 97.457 ms | 0 - 3 MB | W8A16 | NPU | Use Export Script |
|
| 61 |
+
| UnetQuantizable | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 110.665 ms | 0 - 8 MB | W8A16 | NPU | Use Export Script |
|
| 62 |
+
| VaeDecoderQuantizable | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 295.307 ms | 0 - 71 MB | W8A16 | NPU | [Stable-Diffusion-v2.1.so](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/VaeDecoderQuantizable.so) |
|
| 63 |
+
| VaeDecoderQuantizable | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 223.33 ms | 0 - 312 MB | W8A16 | NPU | [Stable-Diffusion-v2.1.so](https://huggingface.co/qualcomm/Stable-Diffusion-v2.1/blob/main/VaeDecoderQuantizable.so) |
|
| 64 |
+
| VaeDecoderQuantizable | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 189.418 ms | 0 - 356 MB | W8A16 | NPU | Use Export Script |
|
| 65 |
+
| VaeDecoderQuantizable | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 267.095 ms | 0 - 0 MB | W8A16 | NPU | Use Export Script |
|
| 66 |
+
| VaeDecoderQuantizable | SA7255P ADP | SA7255P | QNN | 4460.526 ms | 0 - 10 MB | W8A16 | NPU | Use Export Script |
|
| 67 |
+
| VaeDecoderQuantizable | SA8255 (Proxy) | SA8255P Proxy | QNN | 274.71 ms | 0 - 2 MB | W8A16 | NPU | Use Export Script |
|
| 68 |
+
| VaeDecoderQuantizable | SA8650 (Proxy) | SA8650P Proxy | QNN | 269.652 ms | 0 - 2 MB | W8A16 | NPU | Use Export Script |
|
| 69 |
+
| VaeDecoderQuantizable | SA8775P ADP | SA8775P | QNN | 301.141 ms | 0 - 10 MB | W8A16 | NPU | Use Export Script |
|
| 70 |
+
| VaeDecoderQuantizable | QCS8275 (Proxy) | QCS8275 Proxy | QNN | 4460.526 ms | 0 - 10 MB | W8A16 | NPU | Use Export Script |
|
| 71 |
+
| VaeDecoderQuantizable | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 271.222 ms | 0 - 3 MB | W8A16 | NPU | Use Export Script |
|
| 72 |
+
| VaeDecoderQuantizable | QCS9075 (Proxy) | QCS9075 Proxy | QNN | 301.141 ms | 0 - 10 MB | W8A16 | NPU | Use Export Script |
|
| 73 |
|
| 74 |
|
| 75 |
|
|
|
|
| 133 |
TextEncoderQuantizable
|
| 134 |
Device : Samsung Galaxy S23 (13)
|
| 135 |
Runtime : QNN
|
| 136 |
+
Estimated inference time (ms) : 6.7
|
| 137 |
+
Estimated peak memory usage (MB): [0, 3]
|
| 138 |
Total # Ops : 787
|
| 139 |
Compute Unit(s) : NPU (787 ops)
|
| 140 |
|
|
|
|
| 142 |
UnetQuantizable
|
| 143 |
Device : Samsung Galaxy S23 (13)
|
| 144 |
Runtime : QNN
|
| 145 |
+
Estimated inference time (ms) : 97.0
|
| 146 |
Estimated peak memory usage (MB): [0, 3]
|
| 147 |
Total # Ops : 5891
|
| 148 |
Compute Unit(s) : NPU (5891 ops)
|
|
|
|
| 151 |
VaeDecoderQuantizable
|
| 152 |
Device : Samsung Galaxy S23 (13)
|
| 153 |
Runtime : QNN
|
| 154 |
+
Estimated inference time (ms) : 295.3
|
| 155 |
+
Estimated peak memory usage (MB): [0, 71]
|
| 156 |
Total # Ops : 189
|
| 157 |
Compute Unit(s) : NPU (189 ops)
|
| 158 |
```
|