Profile Job Results
Jobs
jp4xm9o25
Results Ready
Name
bevfusion_det_encoder_2
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.7
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
img: float32[1, 6, 256, 32, 88]intrins: float32[1, 6, 3, 3]camera2lidars: float32[1, 6, 4, 4]inv_post_rots: float32[1, 6, 3, 3]post_trans: float32[1, 6, 1, 3]Completion Time
4/5/2026, 8:46:42 AM
Options
--qairt_version 2.42Versions
- ONNX Runtime: 1.24.3
- QAIRT: v2.42.0.251225135753_193295
- Qualcomm Linux: 1.7-ver.1.1
- AI Hub: aihub-2026.03.29.0
Estimated Inference Time
3.60 s
Estimated Peak Memory Usage
233 ‑ 236 MB
Compute Units
NPU
283
| Stage | Time | Memory |
|---|---|---|
First App Load | 922 ms | 41 MB |
Subsequent App Load | 886 ms | 43 MB |
Inference | 3.60 s | 233‑236 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 | "2" |
| 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