Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jp0xk6m2p
Results Ready
Name
pipertts_it_charsiu_decoder
Target Device
  • QCS8550 (Proxy)
  • Android 12
  • Qualcomm® Dragonwing™ QCS8550
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, 6:38:57 PM
Options
--qairt_version latest
Versions
  • QAIRT: v2.51.0.260929181845
  • QNN Backend API: 5.51.0
  • QNN Core API: 2.40.0
  • Android: 13 (TP1A.220624.014)
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
397 μs
Estimated Peak Memory Usage
1 ‑ 3 MB
Compute Units
NPU
213
StageTimeMemory
First App Load
250 ms1‑2 MB
Subsequent App Load
226 ms2‑4 MB
Inference
397 μs1‑3 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