Profile Job Results
Jobs
j56yr2eyp
Results Ready
Name
whisper_base_en_WhisperDecoder
Target Device
- QCS8550 (Proxy)
- Android 12
- Qualcomm® QCS8550
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, 10:01:07 AM
Versions
- QNN: v2.28.2.241116104011_103376
- QNN Backend API: 5.28.0
- QNN Core API: 2.21.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2024.11.22.0
Estimated Inference Time
4.20 ms
Estimated Peak Memory Usage
20 ‑ 22 MB
Compute Units
NPU
821
Stage | Time | Memory |
---|---|---|
First App Load | 300 ms | 1‑2 MB |
Subsequent App Load | 280 ms | 2‑5 MB |
Inference | 4.20 ms | 20‑22 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