Profile Job Results
Jobs
jp487molg
Results Ready
Name
pi05_backbone
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.7
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
hidden_state: float32[1, 968, 2048]prefix_att_2d_masks: float32[1, 1, 968, 968]rope_emb_sin: float32[1, 968, 1, 128]rope_emb_cos: float32[1, 968, 1, 128]Completion Time
6/13/2026, 9:34:24 AM
Versions
- ONNX Runtime: 1.25.0
- QAIRT: v2.45.0.260326154327
- Qualcomm Linux: 1.7-ver.1.1
- AI Hub: aihub-2026.06.08.2
Estimated Inference Time
399 ms
Estimated Peak Memory Usage
12 ‑ 27 MB
Compute Units
NPU
2473
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.01 s | 945‑946 MB |
Subsequent App Load | 1.01 s | 945‑946 MB |
Inference | 399 ms | 12‑27 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