Profile Job Results
Jobs
jgo829x1p
Results Ready
Name
bevdet_encoder
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image: float32[1, 18, 256, 704]Completion Time
7/25/2026, 8:18:15 PM
Versions
- Lite RT: 1.4.4
- QAIRT: v2.45.0.260326154327
- QNN TfLite Delegate: v2.45.0.260326154327
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2026.07.17.0
Estimated Inference Time
38.9 ms
Estimated Peak Memory Usage
2 ‑ 5 MB
Compute Units
NPU
93
| Stage | Time | Memory |
|---|---|---|
First App Load | 12.2 s | 358‑360 MB |
Subsequent App Load | 275 ms | 0‑133 MB |
Inference | 38.9 ms | 2‑5 MB |
| Lite RT | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.optimization_strategy | kHtpOptimizeForInferenceO3 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device