Profile Job Results
Jobs
j5q6z0eop
Results Ready
Name
whisper_base_en_WhisperDecoder
Target Device
- Snapdragon 8 Elite QRD
- Android 15
- Snapdragon® 8 Elite | SM8750
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
x: int32[1, 1]index: int32[1, 1]k_cache_cross: float32[6, 8, 64, 1500]v_cache_cross: float32[6, 8, 1500, 64]k_cache_self: float32[6, 8, 64, 224]v_cache_self: float32[6, 8, 224, 64]Completion Time
11/26/2024, 10:09:17 AM
Versions
- ONNX Runtime: 1.19.2
- QNN: v2.28.2.241116104011_103376
- Android: 15 (AQ3A.240829.003)
- Build ID: Pakala.LA.1.0.r1-01032-STD.PROD-1
- AI Hub: aihub-2024.11.22.0
Estimated Inference Time
12.0 ms
Estimated Peak Memory Usage
28 ‑ 229 MB
Compute Units
NPU
844
| Stage | Time | Memory |
|---|---|---|
First App Load | 28.7 s | 1 GB |
Subsequent App Load | 161 ms | 185‑387 MB |
Inference | 12.0 ms | 28‑229 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" |
Sign up to run this model on a hosted Qualcomm® device!
Run on device