Profile Job Results
Jobs
jn5qd2vmg
Results Ready
Name
whisper_tiny_en_WhisperDecoder
Target Device
- Samsung Galaxy S24+
- Android 14
- Snapdragon® 8 Gen 3 | SM8650
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
x: int32[1, 1]index: int32[1, 1]k_cache_cross: float32[4, 6, 64, 1500]v_cache_cross: float32[4, 6, 1500, 64]k_cache_self: float32[4, 6, 64, 224]v_cache_self: float32[4, 6, 224, 64]Completion Time
8/27/2024, 8:39:47 AM
Versions
- QNN: v2.25.0.240728104910_97711
- QNN Backend API: 5.25.0
- QNN Core API: 2.18.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2024.08.23.0
Estimated Inference Time
1.60 ms
Estimated Peak Memory Usage
4 - 26 MB
Compute Units
NPU
447
| Stage | Time | Memory |
|---|---|---|
First App Load | 889 ms | 440-447 MB |
Subsequent App Load | 629 ms | 7-221 MB |
Inference | 1.60 ms | 4-26 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