Profile Job Results
Jobs
j5m6znd7g
Results Ready
Name
whisper_base_en_WhisperDecoderInf
Target Device
- SA7255P ADP
- Android 14
- Qualcomm® SA7255P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
x: int32[1, 1]index: int32[1, 1]k_cache_self: float16[6, 8, 64, 224]v_cache_self: float16[6, 8, 224, 64]k_cache_cross: float16[6, 8, 64, 1500]v_cache_cross: float16[6, 8, 1500, 64]Completion Time
7/19/2025, 3:26:43 PM
Versions
- QAIRT: v2.34.2.250528164111_119506-auto
- QNN Backend API: 5.34.0
- QNN Core API: 2.25.0
- Android: 14 (UQ1A.240205.002)
- Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00012-STD.PROD-5
- AI Hub: aihub-2025.07.12.0
Estimated Inference Time
6.81 ms
Estimated Peak Memory Usage
11 ‑ 80 MB
Compute Units
NPU
821
| Stage | Time | Memory |
|---|---|---|
First App Load | 15.4 s | 489‑498 MB |
Subsequent App Load | 15.8 s | 490‑641 MB |
Inference | 6.81 ms | 11‑80 MB |
| QNN | Value |
|---|---|
| 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