Profile Job Results
Jobs
j57orlmlg
Results Ready
Name
bevdet_decoder
Target Device
- SA8775P ADP
- Android 14
- Qualcomm® SA8775P
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
bev_feature: float32[1, 64, 128, 128]Completion Time
10/3/2026, 3:35:18 PM
Versions
- Lite RT: 1.4.2
- Android: 14 (UAG2.240908.001)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00016-STD.PROD-3
- AI Hub: aihub-2026.09.25.0
Estimated Inference Time
468 ms
Estimated Peak Memory Usage
1 ‑ 32 MB
Compute Units
GPU
52
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.11 min | 302‑308 MB |
Subsequent App Load | 1.23 s | 207‑240 MB |
Inference | 468 ms | 1‑32 MB |
| Lite RT | Value |
|---|---|
| number_of_threads | 4 |
| GPUv2 Delegate | Value |
|---|---|
| inference_preference | TFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED |
| inference_priority1 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY |
| inference_priority2 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE |
| inference_priority3 | TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION |
Sign up to run this model on a hosted Qualcomm® device!
Run on device