Profile Job Results
Jobs
jp1vyl0np
Results Ready
Name
pi05_token_emb
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.7
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
lang_tokens: int32[1, 200]lang_mask: float32[1, 200]img_embed1: float32[1, 256, 2048]img_embed2: float32[1, 256, 2048]img_embed3: float32[1, 256, 2048]Completion Time
7/4/2026, 1:27:45 PM
Versions
- ONNX Runtime: 1.26.0
- QAIRT: v2.45.0.260326154327
- Qualcomm Linux: 1.7-ver.1.1
- AI Hub: aihub-2026.06.19.2
Estimated Inference Time
4.96 ms
Estimated Peak Memory Usage
6 ‑ 15 MB
Compute Units
NPU
34
| Stage | Time | Memory |
|---|---|---|
First App Load | 579 ms | 1,018‑1,019 MB |
Subsequent App Load | 623 ms | 1,018‑1,019 MB |
Inference | 4.96 ms | 6‑15 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