Profile Job Results
Jobs
jpxkvwx85
Results Ready
Name
whisper_base_en_WhisperDecoder
Target Device
- SA8775P ADP
- Android 14
- Qualcomm® SA8775P
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
1/21/2025, 10:16:49 AM
Versions
- QNN: v2.28.0.241029232508_102474-auto
- QNN Backend API: 5.28.0
- QNN Core API: 2.21.0
- Android: 14 (UQ1A.240205.002)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00011-STD.PROD-1.89321.2
- AI Hub: aihub-2025.01.04.0
Estimated Inference Time
5.66 ms
Estimated Peak Memory Usage
18 ‑ 27 MB
Compute Units
NPU
821
Stage | Time | Memory |
---|---|---|
First App Load | 309 ms | 0‑10 MB |
Subsequent App Load | 322 ms | 0‑10 MB |
Inference | 5.66 ms | 18‑27 MB |
QNN | Value |
---|---|
default_graph_options.htp_options.precision | FLOAT16 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device