Profile Job Results
Jobs
jp4kevmqg
Results Ready
Name
whisper_base_en_WhisperDecoderInf
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: float16[6, 8, 64, 1500]v_cache_cross: float16[6, 8, 1500, 64]k_cache_self: float16[6, 8, 64, 224]v_cache_self: float16[6, 8, 224, 64]Completion Time
5/20/2025, 10:24:21 AM
Versions
- QAIRT: v2.32.6.250402152434_116405
- QNN Backend API: 5.32.0
- QNN Core API: 2.24.0
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2025.05.14.0
Estimated Inference Time
4.25 ms
Estimated Peak Memory Usage
19 ‑ 22 MB
Compute Units
NPU
821
| Stage | Time | Memory |
|---|---|---|
First App Load | 201 ms | 1‑2 MB |
Subsequent App Load | 197 ms | 1‑2 MB |
Inference | 4.25 ms | 19‑22 MB |
| QNN | Value |
|---|---|
| context_options.htp_options.performance_mode | BURST |
| default_graph_options.htp_options.optimizations[0].type | FINALIZE_OPTIMIZATION_FLAG |
| default_graph_options.htp_options.optimizations[0].value | 3.0 |
| default_graph_options.htp_options.precision | FLOAT16 |
| default_graph_options.htp_options.vtcm_size | 0 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device