Profile Job Results
Jobs
j7gj3rdxp
Results Ready
Name
whisper_small_en_WhisperDecoder
Target Device
- SA8650 (Proxy)
- Android 13
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
x: int32[1, 1]index: int32[1, 1]k_cache_cross: float32[12, 12, 64, 1500]v_cache_cross: float32[12, 12, 1500, 64]k_cache_self: float32[12, 12, 64, 224]v_cache_self: float32[12, 12, 224, 64]Completion Time
8/11/2024, 5:53:06 AM
Versions
- QNN: v2.24.0.240626131148_96320
- QNN Backend API: 5.24.0
- QNN Core API: 2.17.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.08.01.0
Estimated Inference Time
12.2 ms
Estimated Peak Memory Usage
61 - 62 MB
Compute Units
NPU
2255
| Stage | Time | Memory |
|---|---|---|
First App Load | 555 ms | 1-2 MB |
Subsequent App Load | 282 ms | 1-6 MB |
Inference | 12.2 ms | 61-62 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.precision | FLOAT16 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device