qaihm-bot commited on
Commit
f1c1fd7
·
verified ·
1 Parent(s): 6a2838f

Upload README.md with huggingface_hub

Browse files
Files changed (1) hide show
  1. README.md +18 -18
README.md CHANGED
@@ -36,22 +36,22 @@ More details on model performance across various devices, can be found
36
 
37
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
- | VITQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 5.278 ms | 0 - 39 MB | INT8 | NPU | [VITQuantized.so](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.so) |
40
- | VITQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 52.233 ms | 2 - 6 MB | INT8 | NPU | [VITQuantized.onnx](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.onnx) |
41
- | VITQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 3.531 ms | 0 - 43 MB | INT8 | NPU | [VITQuantized.so](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.so) |
42
- | VITQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 36.756 ms | 4 - 391 MB | INT8 | NPU | [VITQuantized.onnx](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.onnx) |
43
- | VITQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 3.265 ms | 0 - 64 MB | INT8 | NPU | Use Export Script |
44
- | VITQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 33.562 ms | 2 - 148 MB | INT8 | NPU | [VITQuantized.onnx](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.onnx) |
45
- | VITQuantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 22.553 ms | 0 - 12 MB | INT8 | NPU | Use Export Script |
46
- | VITQuantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 4.724 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
47
- | VITQuantized | SA7255P ADP | SA7255P | QNN | 38.793 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
48
- | VITQuantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 4.772 ms | 0 - 1 MB | INT8 | NPU | Use Export Script |
49
- | VITQuantized | SA8295P ADP | SA8295P | QNN | 6.861 ms | 0 - 6 MB | INT8 | NPU | Use Export Script |
50
- | VITQuantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 4.743 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
51
- | VITQuantized | SA8775P ADP | SA8775P | QNN | 6.287 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
52
- | VITQuantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 6.185 ms | 0 - 48 MB | INT8 | NPU | Use Export Script |
53
- | VITQuantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 5.161 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
54
- | VITQuantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 72.286 ms | 86 - 86 MB | INT8 | NPU | [VITQuantized.onnx](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.onnx) |
55
 
56
 
57
 
@@ -115,8 +115,8 @@ Profiling Results
115
  VITQuantized
116
  Device : Samsung Galaxy S23 (13)
117
  Runtime : QNN
118
- Estimated inference time (ms) : 5.3
119
- Estimated peak memory usage (MB): [0, 39]
120
  Total # Ops : 903
121
  Compute Unit(s) : NPU (903 ops)
122
  ```
 
36
 
37
  | Model | Device | Chipset | Target Runtime | Inference Time (ms) | Peak Memory Range (MB) | Precision | Primary Compute Unit | Target Model
38
  |---|---|---|---|---|---|---|---|---|
39
+ | VITQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | QNN | 5.248 ms | 0 - 184 MB | INT8 | NPU | [VITQuantized.so](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.so) |
40
+ | VITQuantized | Samsung Galaxy S23 | Snapdragon® 8 Gen 2 | ONNX | 39.154 ms | 0 - 155 MB | INT8 | NPU | [VITQuantized.onnx](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.onnx) |
41
+ | VITQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | QNN | 3.522 ms | 0 - 45 MB | INT8 | NPU | [VITQuantized.so](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.so) |
42
+ | VITQuantized | Samsung Galaxy S24 | Snapdragon® 8 Gen 3 | ONNX | 31.231 ms | 0 - 82 MB | INT8 | NPU | [VITQuantized.onnx](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.onnx) |
43
+ | VITQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | QNN | 3.255 ms | 0 - 63 MB | INT8 | NPU | Use Export Script |
44
+ | VITQuantized | Snapdragon 8 Elite QRD | Snapdragon® 8 Elite | ONNX | 33.006 ms | 0 - 83 MB | INT8 | NPU | [VITQuantized.onnx](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.onnx) |
45
+ | VITQuantized | RB3 Gen 2 (Proxy) | QCS6490 Proxy | QNN | 21.663 ms | 0 - 12 MB | INT8 | NPU | Use Export Script |
46
+ | VITQuantized | QCS8550 (Proxy) | QCS8550 Proxy | QNN | 4.73 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
47
+ | VITQuantized | SA7255P ADP | SA7255P | QNN | 38.812 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
48
+ | VITQuantized | SA8255 (Proxy) | SA8255P Proxy | QNN | 4.742 ms | 0 - 2 MB | INT8 | NPU | Use Export Script |
49
+ | VITQuantized | SA8295P ADP | SA8295P | QNN | 6.827 ms | 0 - 15 MB | INT8 | NPU | Use Export Script |
50
+ | VITQuantized | SA8650 (Proxy) | SA8650P Proxy | QNN | 4.735 ms | 0 - 3 MB | INT8 | NPU | Use Export Script |
51
+ | VITQuantized | SA8775P ADP | SA8775P | QNN | 6.256 ms | 0 - 10 MB | INT8 | NPU | Use Export Script |
52
+ | VITQuantized | QCS8450 (Proxy) | QCS8450 Proxy | QNN | 5.956 ms | 0 - 46 MB | INT8 | NPU | Use Export Script |
53
+ | VITQuantized | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN | 5.154 ms | 0 - 0 MB | INT8 | NPU | Use Export Script |
54
+ | VITQuantized | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 51.116 ms | 87 - 87 MB | INT8 | NPU | [VITQuantized.onnx](https://huggingface.co/qualcomm/VITQuantized/blob/main/VITQuantized.onnx) |
55
 
56
 
57
 
 
115
  VITQuantized
116
  Device : Samsung Galaxy S23 (13)
117
  Runtime : QNN
118
+ Estimated inference time (ms) : 5.2
119
+ Estimated peak memory usage (MB): [0, 184]
120
  Total # Ops : 903
121
  Compute Unit(s) : NPU (903 ops)
122
  ```