Profile Job Results
Jobs
jgklo4o25
Results Ready
Name
distil_whisper_decoder
Target Device
- Dragonwing IQ-9075 EVK
- Qualcomm Linux 1.7
- Qualcomm® Dragonwing™ IQ-9075 | QCS9075
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[12, 1, 64, 199]v_cache_self_0_in: float32[12, 1, 199, 64]attention_mask: float32[1, 1, 1, 200]k_cache_cross_0: float32[12, 1, 64, 1500]v_cache_cross_0: float32[12, 1, 1500, 64]k_cache_self_1_in: float32[12, 1, 64, 199]v_cache_self_1_in: float32[12, 1, 199, 64]k_cache_cross_1: float32[12, 1, 64, 1500]v_cache_cross_1: float32[12, 1, 1500, 64]k_cache_self_2_in: float32[12, 1, 64, 199]v_cache_self_2_in: float32[12, 1, 199, 64]k_cache_cross_2: float32[12, 1, 64, 1500]v_cache_cross_2: float32[12, 1, 1500, 64]k_cache_self_3_in: float32[12, 1, 64, 199]v_cache_self_3_in: float32[12, 1, 199, 64]k_cache_cross_3: float32[12, 1, 64, 1500]v_cache_cross_3: float32[12, 1, 1500, 64]Completion Time
4/5/2026, 10:41:59 AM
Versions
- QAIRT: v2.43.0.260127150333_193827
- QNN Backend API: 5.43.0
- QNN Core API: 2.32.0
- Qualcomm Linux: 1.7-ver.1.1
- AI Hub: aihub-2026.03.29.0
Estimated Inference Time
13.1 ms
Estimated Peak Memory Usage
40 ‑ 86 MB
Compute Units
NPU
789
| Stage | Time | Memory |
|---|---|---|
First App Load | 5.73 s | 817 MB |
Subsequent App Load | 271 ms | 3‑4 MB |
Inference | 13.1 ms | 40‑86 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 | 2.0 |
| 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