Profile Job Results
Jobs
jnp1ond75
Results Ready
Name
trocr_TrOCRDecoder
Target Device
- Samsung Galaxy S23 Ultra
- Android 13
- Snapdragon® 8 Gen 2 | SM8550
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
input_ids: int32[1, 1]kv_0_attn_key: float32[1, 8, 1, 32]kv_0_attn_val: float32[1, 8, 1, 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, 1, 32]kv_1_attn_val: float32[1, 8, 1, 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, 1, 32]kv_2_attn_val: float32[1, 8, 1, 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, 1, 32]kv_3_attn_val: float32[1, 8, 1, 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, 1, 32]kv_4_attn_val: float32[1, 8, 1, 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, 1, 32]kv_5_attn_val: float32[1, 8, 1, 32]kv_5_cross_attn_key: float32[1, 8, 578, 32]kv_5_cross_attn_val: float32[1, 8, 578, 32]Completion Time
8/11/2024, 9:57:24 AM
Versions
- TensorFlow Lite: 2.16.1
- QNN TfLite Delegate: v2.24.0.240626131148_96320
- Android: 13 (TP1A.220624.014)
- AI Hub: aihub-2024.08.01.0
Estimated Inference Time
6.49 ms
Estimated Peak Memory Usage
7 - 13 MB
Compute Units
NPU
375
CPU
6
GPU
1
| Stage | Time | Memory |
|---|---|---|
First App Load | 1.77 s | 577-579 MB |
Subsequent App Load | 336 ms | 24-227 MB |
Inference | 6.49 ms | 7-13 MB |
| TensorFlow Lite | Value |
|---|---|
| number_of_threads | 4 |
| QNN Delegate | Value |
|---|---|
| backend_type | kHtpBackend |
| log_level | kLogLevelWarn |
| htp_options.performance_mode | kHtpBurst |
| htp_options.precision | kHtpFp16 |
| htp_options.useConvHmx | true |
| GPUv2 Delegate | Value |
|---|---|
| inference_preference | TFLITE_GPU_INFERENCE_PREFERENCE_SUSTAINED_SPEED |
| inference_priority1 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_LATENCY |
| inference_priority2 | TFLITE_GPU_INFERENCE_PRIORITY_MIN_MEMORY_USAGE |
| inference_priority3 | TFLITE_GPU_INFERENCE_PRIORITY_MAX_PRECISION |
| XNNPACK Delegate | Value |
|---|
Sign up to run this model on a hosted Qualcomm® device!
Run on device