Profile Job Results
Jobs
jgdq3qoz5
Results Ready
Name
whisper_base_en_HfWhisperDecoder
Target Device
- XR2 Gen 2 (Proxy)
- Android 13
- Qualcomm® QCS8450
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
: float16[8, 1, 64, 199]v_cache_self_0_in
: float16[8, 1, 199, 64]attention_mask
: float16[1, 1, 1, 200]k_cache_cross_0
: float16[8, 1, 64, 1500]v_cache_cross_0
: float16[8, 1, 1500, 64]k_cache_self_1_in
: float16[8, 1, 64, 199]v_cache_self_1_in
: float16[8, 1, 199, 64]k_cache_cross_1
: float16[8, 1, 64, 1500]v_cache_cross_1
: float16[8, 1, 1500, 64]k_cache_self_2_in
: float16[8, 1, 64, 199]v_cache_self_2_in
: float16[8, 1, 199, 64]k_cache_cross_2
: float16[8, 1, 64, 1500]v_cache_cross_2
: float16[8, 1, 1500, 64]k_cache_self_3_in
: float16[8, 1, 64, 199]v_cache_self_3_in
: float16[8, 1, 199, 64]k_cache_cross_3
: float16[8, 1, 64, 1500]v_cache_cross_3
: float16[8, 1, 1500, 64]k_cache_self_4_in
: float16[8, 1, 64, 199]v_cache_self_4_in
: float16[8, 1, 199, 64]k_cache_cross_4
: float16[8, 1, 64, 1500]v_cache_cross_4
: float16[8, 1, 1500, 64]k_cache_self_5_in
: float16[8, 1, 64, 199]v_cache_self_5_in
: float16[8, 1, 199, 64]k_cache_cross_5
: float16[8, 1, 64, 1500]v_cache_cross_5
: float16[8, 1, 1500, 64]Completion Time
8/23/2025, 7:42:10 PM
Options
--qairt_version latest
Versions
- QAIRT: v2.37.0.250724175447_124859
- QNN Backend API: 5.37.0
- QNN Core API: 2.27.0
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2025.08.21.0
Estimated Inference Time
5.17 ms
Estimated Peak Memory Usage
17 ‑ 71 MB
Compute Units
NPU
807
Stage | Time | Memory |
---|---|---|
First App Load | 1.65 s | 553‑561 MB |
Subsequent App Load | 1.64 s | 449‑606 MB |
Inference | 5.17 ms | 17‑71 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