Profile Job Results
Jobs
jp2j2mlq5
Results Ready
Name
sam2_decoder
Target Device
- Dragonwing RB3 Gen 2 Vision Kit
- Qualcomm Linux 1.6
- Qualcomm® Dragonwing™ RB3 Gen 2 | QCS6490
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
image_embeddings: uint8[1, 256, 64, 64]high_res_features1: uint8[1, 32, 256, 256]high_res_features2: uint8[1, 64, 128, 128]sparse_embedding: uint8[1, 3, 256]Completion Time
6/14/2026, 5:27:55 AM
Options
--onnx_execution_providers qnnVersions
- ONNX Runtime: 1.25.0
- QAIRT: v2.45.0.260326154327
- Qualcomm Linux: 1.6-ver.1.2
- AI Hub: aihub-2026.06.08.2
Estimated Inference Time
11.0 ms
Estimated Peak Memory Usage
4 ‑ 49 MB
Compute Units
NPU
853
| Stage | Time | Memory |
|---|---|---|
First App Load | 9.12 s | 219‑220 MB |
Subsequent App Load | 528 ms | 100 MB |
Inference | 11.0 ms | 4‑49 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 | "0" |
| 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