Profile Job Results
Jobs
jogk66wy5
Results Ready
Name
openai_clip_CLIPTextEncoder
Target Device
- QCS8550 (Proxy)
- Android 12
Creator
ai-hub-support@qti.qualcomm.com
Target Model
Input Specs
text: int32[1, 77]Completion Time
8/11/2024, 6:57:07 AM
Versions
- TensorFlow Lite: 2.16.1
- QNN TfLite Delegate: v2.24.0.240626131148_96320
- Android: 14 (UP1A.231005.007)
- AI Hub: aihub-2024.08.01.0
Estimated Inference Time
11.6 ms
Estimated Peak Memory Usage
0 - 8 MB
Compute Units
NPU
573
CPU
2
GPU
1
| Stage | Time | Memory |
|---|---|---|
First App Load | 9.20 s | 1 GB |
Subsequent App Load | 344 ms | 1-299 MB |
Inference | 11.6 ms | 0-8 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 |
Sign up to run this model on a hosted Qualcomm® device!
Run on device