Profile Job Results
Jobs
jpe6mkrvg
Results Ready
Name
bevdet_pooler
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® Dragonwing™ QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
depth: float32[1, 6, 59, 16, 44]feat: float32[1, 6, 64, 16, 44]sensor2keyegos: float32[1, 6, 4, 4]inv_intrins: float32[1, 6, 3, 3]inv_post_rots: float32[1, 6, 3, 3]post_trans: float32[1, 6, 1, 3]Completion Time
10/3/2026, 3:56:19 PM
Options
--compute_unit cpuVersions
- ONNX Runtime: 1.30.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.09.25.0
Estimated Inference Time
27.9 ms
Estimated Peak Memory Usage
298 ‑ 299 MB
Compute Units
CPU
279
| Stage | Time | Memory |
|---|---|---|
First App Load | 115 ms | 7‑9 MB |
Subsequent App Load | 63.8 ms | 0‑3 MB |
Inference | 27.9 ms | 298‑299 MB |
| ONNX Runtime | Value |
|---|---|
| execution_mode | SEQUENTIAL |
| intra_op_num_threads | 0 |
| inter_op_num_threads | 0 |
| enable_memory_pattern | false |
| enable_cpu_memory_arena | false |
| graph_optimization_level | ENABLE_ALL |
Sign up to run this model on a hosted Qualcomm® device!
Run on device