Profile Job Results
Jobs
jz5we97m5
Results Ready
Name
controlnet_quantized_UNet_Quantized
Target Device
- Samsung Galaxy S24
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_1: float32[1, 64, 64, 4]input_2: float32[1, 1280]input_3: float32[1, 77, 768]controlnet_downblock1: float32[1, 64, 64, 320]controlnet_downblock2: float32[1, 64, 64, 320]controlnet_downblock3: float32[1, 64, 64, 320]controlnet_downblock4: float32[1, 32, 32, 320]controlnet_downblock5: float32[1, 32, 32, 640]controlnet_downblock6: float32[1, 32, 32, 640]controlnet_downblock7: float32[1, 16, 16, 640]controlnet_downblock8: float32[1, 16, 16, 1280]controlnet_downblock9: float32[1, 16, 16, 1280]controlnet_downblock10: float32[1, 8, 8, 1280]controlnet_downblock11: float32[1, 8, 8, 1280]controlnet_downblock12: float32[1, 8, 8, 1280]controlnet_midblock: float32[1, 8, 8, 1280]Completion Time
3/19/2024, 12:44:52 AM
Versions
- QNN: v2.19.0.240124133650_81096
- QNN Backend API: 5.19.0
- QNN Core API: 2.13.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2024.03.07.0
Estimated Inference Time
193 ms
Estimated Peak Memory Usage
0 - 1 GB
Compute Units
NPU
5434
| Stage | Time | Memory |
|---|---|---|
First App Load | 479 ms | 2-10 MB |
Subsequent App Load | 504 ms | 1-10 MB |
Inference | 193 ms | 0-1 GB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.precision | FLOAT16 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device