Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jgkkddxng
Results Ready
Name
melotts_ko_charsiu_decoder
Target Device
  • Samsung Galaxy S26
  • Android 16
  • Snapdragon® 8 Elite Gen 5 for Galaxy | SM8850-AD
Creator
ai-hub-support@qti.qualcomm.com
Input Specs
input_ids: int32[1, 1]
block_0_past_self_key_states: uint16[1, 6, 49, 64]
position: int32[1, 1]
block_0_past_self_value_states: uint16[1, 6, 49, 64]
block_0_cross_key_states: uint16[1, 6, 50, 64]
encoder_attention_mask: int32[1, 50]
block_0_cross_value_states: uint16[1, 6, 50, 64]
block_1_past_self_key_states: uint16[1, 6, 49, 64]
block_1_past_self_value_states: uint16[1, 6, 49, 64]
block_1_cross_key_states: uint16[1, 6, 50, 64]
block_1_cross_value_states: uint16[1, 6, 50, 64]
block_2_past_self_key_states: uint16[1, 6, 49, 64]
block_2_past_self_value_states: uint16[1, 6, 49, 64]
block_2_cross_key_states: uint16[1, 6, 50, 64]
block_2_cross_value_states: uint16[1, 6, 50, 64]
block_3_past_self_key_states: uint16[1, 6, 49, 64]
block_3_past_self_value_states: uint16[1, 6, 49, 64]
block_3_cross_key_states: uint16[1, 6, 50, 64]
block_3_cross_value_states: uint16[1, 6, 50, 64]
Completion Time
11/14/2026, 3:24:42 PM
Options
--qairt_version latest
Versions
  • QAIRT: v2.51.0.260929181845
  • QNN Backend API: 5.51.0
  • QNN Core API: 2.40.0
  • Android: 16 (BP4A.251205.006)
  • AI Hub: aihub-2026.11.06.1
Estimated Inference Time
312 μs
Estimated Peak Memory Usage
0 ‑ 7 MB
Compute Units
NPU
294
StageTimeMemory
First App Load
113 ms1‑10 MB
Subsequent App Load
116 ms1‑9 MB
Inference
312 μs0‑7 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
default_graph_options.htp_options.enable_precision_compensationtrue

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

Run on device