Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jgnl6elv5
Results Ready
Name
whisper_base_en_WhisperDecoderInf
Target Device
  • Snapdragon X Elite CRD
  • Windows 11
  • Snapdragon® X Elite | SC8380XP
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
x: int32[1, 1]
index: int32[1, 1]
k_cache_cross: float32[6, 8, 64, 1500]
v_cache_cross: float32[6, 8, 1500, 64]
k_cache_self: float32[6, 8, 64, 224]
v_cache_self: float32[6, 8, 224, 64]
Completion Time
4/8/2025, 9:36:24 AM
Versions
  • ONNX Runtime: 1.21.0+ (commit a46d212)
  • QAIRT: v2.32.0.250228225014_116386
  • Windows: Windows 11 (26100)
  • Build ID: APSS.WP_HA.1.0.c90-07350-SC8380XPSRSFNWZA-2
  • AI Hub: aihub-2025.03.24.0
Estimated Inference Time
9.21 ms
Estimated Peak Memory Usage
106 MB
Compute Units
NPU
845
StageTimeMemory
First App Load
17.6 s1 GB
Subsequent App Load
422 ms165 MB
Inference
9.21 ms106 MB
ONNX RuntimeValue
execution_modeSEQUENTIAL
intra_op_num_threads0
inter_op_num_threads0
enable_memory_patternfalse
enable_cpu_memory_arenafalse
graph_optimization_levelENABLE_ALL
QNN Execution ProviderValue
htp_performance_mode"burst"
htp_graph_finalization_optimization_mode"3"
enable_htp_fp16_precision"1"

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

Run on device