Profile Job Results
Jobs
jp4vd99lp
Results Ready
Name
whisper_large_v3_turbo_float_HfWhisperDecoder
Target Device
- SA8650 (Proxy)
- Android 13
- Qualcomm® SA8650P
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_ids: int32[1, 1]position_ids: int32[1]k_cache_self_0_in: float32[20, 1, 64, 199]v_cache_self_0_in: float32[20, 1, 199, 64]attention_mask: float32[1, 1, 1, 200]k_cache_cross_0: float32[20, 1, 64, 1500]v_cache_cross_0: float32[20, 1, 1500, 64]k_cache_self_1_in: float32[20, 1, 64, 199]v_cache_self_1_in: float32[20, 1, 199, 64]k_cache_cross_1: float32[20, 1, 64, 1500]v_cache_cross_1: float32[20, 1, 1500, 64]k_cache_self_2_in: float32[20, 1, 64, 199]v_cache_self_2_in: float32[20, 1, 199, 64]k_cache_cross_2: float32[20, 1, 64, 1500]v_cache_cross_2: float32[20, 1, 1500, 64]k_cache_self_3_in: float32[20, 1, 64, 199]v_cache_self_3_in: float32[20, 1, 199, 64]k_cache_cross_3: float32[20, 1, 64, 1500]v_cache_cross_3: float32[20, 1, 1500, 64]Completion Time
10/25/2025, 2:52:52 PM
Options
--qairt_version latestVersions
- QAIRT: v2.39.0.250925215840_163802
- QNN Backend API: 5.39.0
- QNN Core API: 2.29.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.10.21.0
Estimated Inference Time
13.1 ms
Estimated Peak Memory Usage
66 ‑ 70 MB
Compute Units
NPU
1222
| Stage | Time | Memory |
|---|---|---|
First App Load | 501 ms | 1‑2 MB |
Subsequent App Load | 453 ms | 1‑7 MB |
Inference | 13.1 ms | 66‑70 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