qaihm-bot commited on
Commit
34fde6f
·
verified ·
1 Parent(s): c7f8027

See https://github.com/quic/ai-hub-models/releases/v0.34.3 for changelog.

Files changed (2) hide show
  1. README.md +0 -3
  2. sdk_versions.yml +9 -0
README.md CHANGED
@@ -87,7 +87,6 @@ More details on model performance across various devices, can be found
87
  | Segformer-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 13.085 ms | 0 - 0 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
88
  | Segformer-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 44.478 ms | 58 - 58 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx) |
89
  | Segformer-Base | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 23.197 ms | 2 - 40 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
90
- | Segformer-Base | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | QNN_DLC | 12.531 ms | 1 - 33 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
91
  | Segformer-Base | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 13.33 ms | 2 - 48 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
92
  | Segformer-Base | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 7.891 ms | 1 - 42 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
93
  | Segformer-Base | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 12.944 ms | 2 - 18 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
@@ -98,11 +97,9 @@ More details on model performance across various devices, can be found
98
  | Segformer-Base | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 25.991 ms | 1 - 48 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
99
  | Segformer-Base | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 363.712 ms | 13 - 29 MB | CPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
100
  | Segformer-Base | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 23.197 ms | 2 - 40 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
101
- | Segformer-Base | w8a8 | SA7255P ADP | Qualcomm® SA7255P | QNN_DLC | 12.531 ms | 1 - 33 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
102
  | Segformer-Base | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 12.935 ms | 2 - 14 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
103
  | Segformer-Base | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 6.906 ms | 1 - 10 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
104
  | Segformer-Base | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 15.162 ms | 2 - 42 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
105
- | Segformer-Base | w8a8 | SA8295P ADP | Qualcomm® SA8295P | QNN_DLC | 8.718 ms | 1 - 35 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
106
  | Segformer-Base | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 12.927 ms | 2 - 15 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
107
  | Segformer-Base | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 6.92 ms | 1 - 10 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
108
  | Segformer-Base | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 13.503 ms | 2 - 41 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
 
87
  | Segformer-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | QNN_DLC | 13.085 ms | 0 - 0 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.dlc) |
88
  | Segformer-Base | w8a16 | Snapdragon X Elite CRD | Snapdragon® X Elite | ONNX | 44.478 ms | 58 - 58 MB | NPU | [Segformer-Base.onnx](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a16.onnx) |
89
  | Segformer-Base | w8a8 | QCS8275 (Proxy) | Qualcomm® QCS8275 (Proxy) | TFLITE | 23.197 ms | 2 - 40 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
 
90
  | Segformer-Base | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | TFLITE | 13.33 ms | 2 - 48 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
91
  | Segformer-Base | w8a8 | QCS8450 (Proxy) | Qualcomm® QCS8450 (Proxy) | QNN_DLC | 7.891 ms | 1 - 42 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
92
  | Segformer-Base | w8a8 | QCS8550 (Proxy) | Qualcomm® QCS8550 (Proxy) | TFLITE | 12.944 ms | 2 - 18 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
 
97
  | Segformer-Base | w8a8 | RB3 Gen 2 (Proxy) | Qualcomm® QCS6490 (Proxy) | QNN_DLC | 25.991 ms | 1 - 48 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
98
  | Segformer-Base | w8a8 | RB5 (Proxy) | Qualcomm® QCS8250 (Proxy) | TFLITE | 363.712 ms | 13 - 29 MB | CPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
99
  | Segformer-Base | w8a8 | SA7255P ADP | Qualcomm® SA7255P | TFLITE | 23.197 ms | 2 - 40 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
 
100
  | Segformer-Base | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | TFLITE | 12.935 ms | 2 - 14 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
101
  | Segformer-Base | w8a8 | SA8255 (Proxy) | Qualcomm® SA8255P (Proxy) | QNN_DLC | 6.906 ms | 1 - 10 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
102
  | Segformer-Base | w8a8 | SA8295P ADP | Qualcomm® SA8295P | TFLITE | 15.162 ms | 2 - 42 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
 
103
  | Segformer-Base | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | TFLITE | 12.927 ms | 2 - 15 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
104
  | Segformer-Base | w8a8 | SA8650 (Proxy) | Qualcomm® SA8650P (Proxy) | QNN_DLC | 6.92 ms | 1 - 10 MB | NPU | [Segformer-Base.dlc](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.dlc) |
105
  | Segformer-Base | w8a8 | SA8775P ADP | Qualcomm® SA8775P | TFLITE | 13.503 ms | 2 - 41 MB | NPU | [Segformer-Base.tflite](https://huggingface.co/qualcomm/Segformer-Base/blob/main/Segformer-Base_w8a8.tflite) |
sdk_versions.yml ADDED
@@ -0,0 +1,9 @@
 
 
 
 
 
 
 
 
 
 
1
+ sdk_versions:
2
+ tflite:
3
+ qairt: 2.34.2.250528164111_119506
4
+ tflite: 2.17.0
5
+ qnn_dlc:
6
+ qairt: 2.34.2.250528164111_119506
7
+ onnx:
8
+ qairt: 2.34.2.250528164111_119506
9
+ onnx_runtime: 1.22.0