Qualcomm® AI HubAI Hub

Profile Job Results

Jobs
jpx0kn23p
Results Ready
Name
trocr_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
input_ids: int32[1, 1]
index: int32[1]
kv_0_attn_key: float32[1, 8, 19, 32]
kv_0_attn_val: float32[1, 8, 19, 32]
kv_0_cross_attn_key: float32[1, 8, 578, 32]
kv_0_cross_attn_val: float32[1, 8, 578, 32]
kv_1_attn_key: float32[1, 8, 19, 32]
kv_1_attn_val: float32[1, 8, 19, 32]
kv_1_cross_attn_key: float32[1, 8, 578, 32]
kv_1_cross_attn_val: float32[1, 8, 578, 32]
kv_2_attn_key: float32[1, 8, 19, 32]
kv_2_attn_val: float32[1, 8, 19, 32]
kv_2_cross_attn_key: float32[1, 8, 578, 32]
kv_2_cross_attn_val: float32[1, 8, 578, 32]
kv_3_attn_key: float32[1, 8, 19, 32]
kv_3_attn_val: float32[1, 8, 19, 32]
kv_3_cross_attn_key: float32[1, 8, 578, 32]
kv_3_cross_attn_val: float32[1, 8, 578, 32]
kv_4_attn_key: float32[1, 8, 19, 32]
kv_4_attn_val: float32[1, 8, 19, 32]
kv_4_cross_attn_key: float32[1, 8, 578, 32]
kv_4_cross_attn_val: float32[1, 8, 578, 32]
kv_5_attn_key: float32[1, 8, 19, 32]
kv_5_attn_val: float32[1, 8, 19, 32]
kv_5_cross_attn_key: float32[1, 8, 578, 32]
kv_5_cross_attn_val: float32[1, 8, 578, 32]
Completion Time
10/4/2026, 9:29:34 PM
Versions
  • Lite RT: 1.4.2
  • QAIRT: v2.50.0.260828221209
  • QNN TfLite Delegate: v2.50.0.260828221209
  • Qualcomm Linux: 1.9-ver.1.0
  • AI Hub: aihub-2026.09.25.0
Estimated Inference Time
2.60 ms
Estimated Peak Memory Usage
0 ‑ 83 MB
Compute Units
NPU
386
StageTimeMemory
First App Load
4.27 s253‑254 MB
Subsequent App Load
230 ms76‑77 MB
Inference
2.60 ms0‑83 MB
Lite RTValue
number_of_threads4
QNN DelegateValue
backend_typekHtpBackend
log_levelkLogLevelWarn
htp_options.performance_modekHtpBurst
htp_options.precisionkHtpFp16
htp_options.optimization_strategykHtpOptimizeForInferenceO3
htp_options.useConvHmxtrue

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

Run on device