| 2025-08-18 22:31:41 - INFO - Loading model: Qwen/Qwen2-VL-2B-Instruct-AWQ | |
| 2025-08-18 22:31:44 - INFO - We will use 90% of the memory on device 0 for storing the model, and 10% for the buffer to avoid OOM. You can set `max_memory` in to a higher value to use more memory (at your own risk). | |
| 2025-08-18 22:31:53 - INFO - Model loaded in 12.48 seconds | |
| 2025-08-18 22:31:53 - INFO - GPU Memory Usage after model load: 2.31 GB | |
| 2025-08-18 22:32:49 - INFO - [a0e31fc7-179a-419d-b6eb-a6f05bc2a73f] Received new video inference request. Prompt: 'Please describe the video.', Video: 'messi_part_001.mp4' | |
| 2025-08-18 22:32:49 - INFO - [a0e31fc7-179a-419d-b6eb-a6f05bc2a73f] Video saved to temporary file: temp_videos/a0e31fc7-179a-419d-b6eb-a6f05bc2a73f.mp4 | |
| 2025-08-18 22:32:49 - INFO - [a0e31fc7-179a-419d-b6eb-a6f05bc2a73f] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-18 22:32:53 - INFO - [a0e31fc7-179a-419d-b6eb-a6f05bc2a73f] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-18 22:32:53 - INFO - [a0e31fc7-179a-419d-b6eb-a6f05bc2a73f] 30 frames saved to temp_videos/a0e31fc7-179a-419d-b6eb-a6f05bc2a73f | |
| 2025-08-18 22:32:54 - INFO - Prompt token length: 2276 | |
| 2025-08-18 22:33:04 - INFO - Tokens per second: 9.100198479728341, Peak GPU memory MB: 4498.375 | |
| 2025-08-18 22:33:04 - INFO - [a0e31fc7-179a-419d-b6eb-a6f05bc2a73f] Inference time: 14.89 seconds, CPU usage: 0.0%, CPU core utilization: [0.0, 0.0, 0.0, 0.0] | |
| 2025-08-18 22:33:04 - INFO - [a0e31fc7-179a-419d-b6eb-a6f05bc2a73f] Cleaned up temporary file: temp_videos/a0e31fc7-179a-419d-b6eb-a6f05bc2a73f.mp4 | |
| 2025-08-18 22:33:04 - INFO - [a0e31fc7-179a-419d-b6eb-a6f05bc2a73f] Cleaned up temporary frame directory: temp_videos/a0e31fc7-179a-419d-b6eb-a6f05bc2a73f | |