Profile Job Results

Jobs
jp1ekw47g
Results Ready
Name
whisper_small_float_HfWhisperDecoder
Target Device
  • SA7255P ADP
  • Android 14
  • Qualcomm® SA7255P
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[12, 1, 64, 199]
v_cache_self_0_in: float16[12, 1, 199, 64]
attention_mask: float16[1, 1, 1, 200]
k_cache_cross_0: float16[12, 1, 64, 1500]
v_cache_cross_0: float16[12, 1, 1500, 64]
k_cache_self_1_in: float16[12, 1, 64, 199]
v_cache_self_1_in: float16[12, 1, 199, 64]
k_cache_cross_1: float16[12, 1, 64, 1500]
v_cache_cross_1: float16[12, 1, 1500, 64]
k_cache_self_2_in: float16[12, 1, 64, 199]
v_cache_self_2_in: float16[12, 1, 199, 64]
k_cache_cross_2: float16[12, 1, 64, 1500]
v_cache_cross_2: float16[12, 1, 1500, 64]
k_cache_self_3_in: float16[12, 1, 64, 199]
v_cache_self_3_in: float16[12, 1, 199, 64]
k_cache_cross_3: float16[12, 1, 64, 1500]
v_cache_cross_3: float16[12, 1, 1500, 64]
k_cache_self_4_in: float16[12, 1, 64, 199]
v_cache_self_4_in: float16[12, 1, 199, 64]
k_cache_cross_4: float16[12, 1, 64, 1500]
v_cache_cross_4: float16[12, 1, 1500, 64]
k_cache_self_5_in: float16[12, 1, 64, 199]
v_cache_self_5_in: float16[12, 1, 199, 64]
k_cache_cross_5: float16[12, 1, 64, 1500]
v_cache_cross_5: float16[12, 1, 1500, 64]
k_cache_self_6_in: float16[12, 1, 64, 199]
v_cache_self_6_in: float16[12, 1, 199, 64]
k_cache_cross_6: float16[12, 1, 64, 1500]
v_cache_cross_6: float16[12, 1, 1500, 64]
k_cache_self_7_in: float16[12, 1, 64, 199]
v_cache_self_7_in: float16[12, 1, 199, 64]
k_cache_cross_7: float16[12, 1, 64, 1500]
v_cache_cross_7: float16[12, 1, 1500, 64]
k_cache_self_8_in: float16[12, 1, 64, 199]
v_cache_self_8_in: float16[12, 1, 199, 64]
k_cache_cross_8: float16[12, 1, 64, 1500]
v_cache_cross_8: float16[12, 1, 1500, 64]
k_cache_self_9_in: float16[12, 1, 64, 199]
v_cache_self_9_in: float16[12, 1, 199, 64]
k_cache_cross_9: float16[12, 1, 64, 1500]
v_cache_cross_9: float16[12, 1, 1500, 64]
k_cache_self_10_in: float16[12, 1, 64, 199]
v_cache_self_10_in: float16[12, 1, 199, 64]
k_cache_cross_10: float16[12, 1, 64, 1500]
v_cache_cross_10: float16[12, 1, 1500, 64]
k_cache_self_11_in: float16[12, 1, 64, 199]
v_cache_self_11_in: float16[12, 1, 199, 64]
k_cache_cross_11: float16[12, 1, 64, 1500]
v_cache_cross_11: float16[12, 1, 1500, 64]
Completion Time
12/13/2025, 4:48:51 PM
Versions
  • QAIRT: v2.40.0.251030114326_189385-auto
  • QNN Backend API: 5.40.0
  • QNN Core API: 2.30.0
  • Android: 14 (UQ1A.240205.002)
  • Build ID: Snapdragon_Auto.HQX.4.5.6.0.r2-00012-STD.PROD-5
  • AI Hub: aihub-2025.12.07.0
Estimated Inference Time
18.7 ms
Estimated Peak Memory Usage
52 ‑ 61 MB
Compute Units
NPU
2302
StageTimeMemory
First App Load
696 ms8‑17 MB
Subsequent App Load
640 ms0‑10 MB
Inference
18.7 ms52‑61 MB
QNNValue
default_graph_options.htp_options.optimizations[0].typeFINALIZE_OPTIMIZATION_FLAG
default_graph_options.htp_options.optimizations[0].value3.0
default_graph_options.htp_options.precisionFLOAT16
default_graph_options.htp_options.vtcm_size0

Sign up to run this model on a hosted Qualcomm® device!

Run on device