Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jpen43e0p
Results Ready
Name
pipertts_en_charsiu_decoder
Target Device
  • Dragonwing IQ-9075 EVK
  • Qualcomm Linux 1.9
  • Qualcomm® Dragonwing™ IQ-9075 | QCS9075
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
block_3_cross_key_states: float32[1, 6, 50, 64]
block_2_cross_key_states: float32[1, 6, 50, 64]
block_1_cross_key_states: float32[1, 6, 50, 64]
block_0_cross_key_states: float32[1, 6, 50, 64]
input_ids: int32[1, 1]
block_0_past_self_key_states: float32[1, 6, 49, 64]
position: int32[1, 1]
block_0_past_self_value_states: float32[1, 6, 49, 64]
encoder_attention_mask: int32[1, 50]
block_0_cross_value_states: float32[1, 6, 50, 64]
block_1_past_self_key_states: float32[1, 6, 49, 64]
block_1_past_self_value_states: float32[1, 6, 49, 64]
block_1_cross_value_states: float32[1, 6, 50, 64]
block_2_past_self_key_states: float32[1, 6, 49, 64]
block_2_past_self_value_states: float32[1, 6, 49, 64]
block_2_cross_value_states: float32[1, 6, 50, 64]
block_3_past_self_key_states: float32[1, 6, 49, 64]
block_3_past_self_value_states: float32[1, 6, 49, 64]
block_3_cross_value_states: float32[1, 6, 50, 64]
Completion Time
11/14/2026, 7:56:17 AM
Options
--qairt_version latest
Versions
  • QAIRT: v2.51.0.260929181845
  • QNN Backend API: 5.51.0
  • QNN Core API: 2.40.0
  • Qualcomm Linux: 1.9-ver.1.0
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
441 μs
Estimated Peak Memory Usage
3 ‑ 6 MB
Compute Units
NPU
213
StageTimeMemory
First App Load
210 ms2‑3 MB
Subsequent App Load
188 ms2‑3 MB
Inference
441 μs3‑6 MB
QNNValue
context_options.htp_options.performance_modeBURST
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