| 2025-08-19 01:05:23 - INFO - Loading model: google/gemma-3-4b-it | |
| 2025-08-19 01:05:24 - 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). | |
| 2025-08-19 01:05:41 - INFO - Model loaded in 17.79 seconds | |
| 2025-08-19 01:05:41 - INFO - GPU Memory Usage after model load: 8201.85 MB | |
| 2025-08-19 01:05:53 - INFO - [918ef8af-5a2d-4683-95b6-92a2aa6dbe57] Received new video inference request. Prompt: 'Please describe the video.', Video: 'messi_part_001.mp4' | |
| 2025-08-19 01:05:53 - INFO - [918ef8af-5a2d-4683-95b6-92a2aa6dbe57] Video saved to temporary file: temp_videos/918ef8af-5a2d-4683-95b6-92a2aa6dbe57.mp4 | |
| 2025-08-19 01:05:53 - INFO - [918ef8af-5a2d-4683-95b6-92a2aa6dbe57] Extracting frames using method: uniform, rate/threshold: 1 | |
| 2025-08-19 01:05:53 - INFO - [918ef8af-5a2d-4683-95b6-92a2aa6dbe57] Extracted 1 frames successfully. Saving to temporary files... | |
| 2025-08-19 01:05:53 - INFO - [918ef8af-5a2d-4683-95b6-92a2aa6dbe57] 1 frames saved to temp_videos/918ef8af-5a2d-4683-95b6-92a2aa6dbe57 | |
| 2025-08-19 01:05:53 - INFO - Prompt token length: 281 | |