Profile Job Results
Jobs
j56y3wknp
Results Ready
Name
whisper_small_en_WhisperDecoder
Target Device
- Snapdragon 8 Elite QRD
- Android 15
- Snapdragon® 8 Elite | SM8750
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
x: int32[1, 1]index: int32[1, 1]k_cache_cross: float32[12, 12, 64, 1500]v_cache_cross: float32[12, 12, 1500, 64]k_cache_self: float32[12, 12, 64, 224]v_cache_self: float32[12, 12, 224, 64]Completion Time
11/10/2024, 6:31:40 AM
Versions
- TensorFlow Lite: 2.17.0
- QNN TfLite Delegate: v2.27.1.240926142112_100894
- Android: 15 (AQ3A.240829.003)
- Build ID: Pakala.LA.1.0.r1-01032-STD.PROD-1
- AI Hub: aihub-2024.10.28.0
Estimated Inference Time
16.6 ms
Estimated Peak Memory Usage
16 ‑ 263 MB
Compute Units
NPU
2573
| Stage | Time | Memory |
|---|---|---|
First App Load | 17.6 s | 4 GB |
Subsequent App Load | 246 ms | 376‑627 MB |
Inference | 16.6 ms | 16‑263 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.useConvHmx | true |
Sign up to run this model on a hosted Qualcomm® device!
Run on device