Profile Job Results
Jobs
j5wd0dx4g
Results Ready
Name
bevfusion_det_decoder
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
x: float32[1, 80, 128, 128]Completion Time
4/18/2026, 11:26:14 PM
Options
--qairt_version 2.42Versions
- ONNX Runtime: 1.24.3
- QAIRT: v2.42.0.251225135753_193295
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2026.04.13.0
Estimated Inference Time
12.6 ms
Estimated Peak Memory Usage
4 ‑ 32 MB
Compute Units
NPU
158
| Stage | Time | Memory |
|---|---|---|
First App Load | 265 ms | 35‑37 MB |
Subsequent App Load | 199 ms | 20‑22 MB |
Inference | 12.6 ms | 4‑32 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 |
| QNN Execution Provider | Value |
|---|---|
| htp_performance_mode | "burst" |
| htp_graph_finalization_optimization_mode | "3" |
| enable_htp_fp16_precision | "1" |
| capture_network_visualizations | false |
| context_priority | "normal" |
| offload_graph_io_quantization | "1" |
Sign up to run this model on a hosted Qualcomm® device!
Run on device