| 2025-08-18 23:48:37 - INFO - Loading model: LiquidAI/LFM2-VL-1.6B | |
| 2025-08-18 23:48:38 - 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 23:48:44 - INFO - Model loaded in 7.31 seconds | |
| 2025-08-18 23:48:44 - INFO - GPU Memory Usage after model load: 3023.64 MB | |
| 2025-08-18 23:49:06 - INFO - [20d53a50-ffe8-4d54-94e1-cd4a287c9be8] Received new video inference request. Prompt: 'Please describe the video.', Video: 'messi_part_001.mp4' | |
| 2025-08-18 23:49:06 - INFO - [20d53a50-ffe8-4d54-94e1-cd4a287c9be8] Video saved to temporary file: temp_videos/20d53a50-ffe8-4d54-94e1-cd4a287c9be8.mp4 | |
| 2025-08-18 23:49:06 - INFO - [20d53a50-ffe8-4d54-94e1-cd4a287c9be8] Extracting frames using method: uniform, rate/threshold: 30 | |
| 2025-08-18 23:49:09 - INFO - [20d53a50-ffe8-4d54-94e1-cd4a287c9be8] Extracted 30 frames successfully. Saving to temporary files... | |
| 2025-08-18 23:49:09 - INFO - [20d53a50-ffe8-4d54-94e1-cd4a287c9be8] 30 frames saved to temp_videos/20d53a50-ffe8-4d54-94e1-cd4a287c9be8 | |
| 2025-08-18 23:49:10 - INFO - Prompt token length: 3584 | |
| 2025-08-18 23:49:27 - INFO - Tokens per second: 34.94049134256706, Peak GPU memory MB: 9376.375 | |
| 2025-08-18 23:49:27 - INFO - [20d53a50-ffe8-4d54-94e1-cd4a287c9be8] Inference time: 20.83 seconds, CPU usage: 63.8%, CPU core utilization: [60.4, 62.1, 69.4, 63.2] | |
| 2025-08-18 23:49:27 - INFO - [20d53a50-ffe8-4d54-94e1-cd4a287c9be8] Cleaned up temporary file: temp_videos/20d53a50-ffe8-4d54-94e1-cd4a287c9be8.mp4 | |
| 2025-08-18 23:49:27 - INFO - [20d53a50-ffe8-4d54-94e1-cd4a287c9be8] Cleaned up temporary frame directory: temp_videos/20d53a50-ffe8-4d54-94e1-cd4a287c9be8 | |