|
2025-08-20 23:17:14 - INFO - Loading model: LiquidAI/LFM2-VL-1.6B |
|
2025-08-20 23:17:16 - 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). |
|
2025-08-20 23:17:22 - INFO - Model loaded in 7.52 seconds |
|
2025-08-20 23:17:22 - INFO - GPU Memory Usage after model load: 3023.64 MB |
|
2025-08-20 23:18:11 - INFO - [7395856c-f721-471f-85da-b8268191bd53] Received new video inference request. Prompt: 'Please describe the video in detail, only focus on customer and staff behavior and activities and do not overly describe the static scene.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_001.mp4' |
|
2025-08-20 23:18:11 - INFO - [7395856c-f721-471f-85da-b8268191bd53] Video saved to temporary file: temp_videos/7395856c-f721-471f-85da-b8268191bd53.mp4 |
|
2025-08-20 23:18:11 - INFO - [7395856c-f721-471f-85da-b8268191bd53] Extracting frames using method: uniform, rate/threshold: 30 |
|
2025-08-20 23:18:16 - INFO - [7395856c-f721-471f-85da-b8268191bd53] Extracted 30 frames successfully. Saving to temporary files... |
|
2025-08-20 23:18:16 - INFO - [7395856c-f721-471f-85da-b8268191bd53] 30 frames saved to temp_videos/7395856c-f721-471f-85da-b8268191bd53 |
|
2025-08-20 23:18:16 - INFO - Prompt token length: 3604 |
|
2025-08-20 23:18:36 - INFO - Tokens per second: 43.071821438037745, Peak GPU memory MB: 9378.375 |
|
2025-08-20 23:18:36 - INFO - [7395856c-f721-471f-85da-b8268191bd53] Inference time: 24.96 seconds, CPU usage: 27.5%, CPU core utilization: [19.8, 26.4, 21.3, 42.5] |
|
2025-08-20 23:18:36 - INFO - [7395856c-f721-471f-85da-b8268191bd53] Cleaned up temporary frame directory: temp_videos/7395856c-f721-471f-85da-b8268191bd53 |
|
2025-08-20 23:18:36 - INFO - [d8cb0a25-8bb0-4b63-9b5a-30f5dc54fd7a] Received new video inference request. Prompt: 'Please describe the video in detail, only focus on customer and staff behavior and activities and do not overly describe the static scene.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_001.mp4' |
|
2025-08-20 23:18:36 - INFO - [d8cb0a25-8bb0-4b63-9b5a-30f5dc54fd7a] Video saved to temporary file: temp_videos/d8cb0a25-8bb0-4b63-9b5a-30f5dc54fd7a.mp4 |
|
2025-08-20 23:18:36 - INFO - [d8cb0a25-8bb0-4b63-9b5a-30f5dc54fd7a] Extracting frames using method: uniform, rate/threshold: 30 |
|
2025-08-20 23:18:41 - INFO - [d8cb0a25-8bb0-4b63-9b5a-30f5dc54fd7a] Extracted 30 frames successfully. Saving to temporary files... |
|
2025-08-20 23:18:41 - INFO - [d8cb0a25-8bb0-4b63-9b5a-30f5dc54fd7a] 30 frames saved to temp_videos/d8cb0a25-8bb0-4b63-9b5a-30f5dc54fd7a |
|
2025-08-20 23:18:41 - INFO - Prompt token length: 3604 |
|
2025-08-20 23:19:01 - INFO - Tokens per second: 43.41840127709154, Peak GPU memory MB: 9378.375 |
|
2025-08-20 23:19:01 - INFO - [d8cb0a25-8bb0-4b63-9b5a-30f5dc54fd7a] Inference time: 24.87 seconds, CPU usage: 38.8%, CPU core utilization: [32.1, 40.6, 19.5, 63.0] |
|
2025-08-20 23:19:01 - INFO - [d8cb0a25-8bb0-4b63-9b5a-30f5dc54fd7a] Cleaned up temporary frame directory: temp_videos/d8cb0a25-8bb0-4b63-9b5a-30f5dc54fd7a |
|
2025-08-20 23:20:04 - INFO - [9679be14-bd46-4299-ad82-b4bab2ae763c] Received new video inference request. Prompt: 'Please describe the video in detail, only focus on customer and staff behavior and activities and do not overly describe the static scene.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_001.mp4' |
|
2025-08-20 23:20:04 - INFO - [9679be14-bd46-4299-ad82-b4bab2ae763c] Video saved to temporary file: temp_videos/9679be14-bd46-4299-ad82-b4bab2ae763c.mp4 |
|
2025-08-20 23:20:04 - INFO - [9679be14-bd46-4299-ad82-b4bab2ae763c] Extracting frames using method: uniform, rate/threshold: 30 |
|
2025-08-20 23:20:08 - INFO - [9679be14-bd46-4299-ad82-b4bab2ae763c] Extracted 30 frames successfully. Saving to temporary files... |
|
2025-08-20 23:20:08 - INFO - [9679be14-bd46-4299-ad82-b4bab2ae763c] 30 frames saved to temp_videos/9679be14-bd46-4299-ad82-b4bab2ae763c |
|
2025-08-20 23:20:09 - INFO - Prompt token length: 3604 |
|
2025-08-20 23:20:28 - INFO - Tokens per second: 43.04488796653849, Peak GPU memory MB: 9378.375 |
|
2025-08-20 23:20:28 - INFO - [9679be14-bd46-4299-ad82-b4bab2ae763c] Inference time: 24.78 seconds, CPU usage: 14.3%, CPU core utilization: [8.6, 10.9, 9.3, 28.5] |
|
2025-08-20 23:20:28 - INFO - [9679be14-bd46-4299-ad82-b4bab2ae763c] Cleaned up temporary frame directory: temp_videos/9679be14-bd46-4299-ad82-b4bab2ae763c |
|
2025-08-20 23:20:28 - INFO - [3d9610ba-18fc-4512-876c-62775d568781] Received new video inference request. Prompt: 'Please describe the video in detail, only focus on customer and staff behavior and activities and do not overly describe the static scene.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_001.mp4' |
|
2025-08-20 23:20:28 - INFO - [3d9610ba-18fc-4512-876c-62775d568781] Video saved to temporary file: temp_videos/3d9610ba-18fc-4512-876c-62775d568781.mp4 |
|
2025-08-20 23:20:28 - INFO - [3d9610ba-18fc-4512-876c-62775d568781] Extracting frames using method: uniform, rate/threshold: 30 |
|
2025-08-20 23:20:33 - INFO - [3d9610ba-18fc-4512-876c-62775d568781] Extracted 30 frames successfully. Saving to temporary files... |
|
2025-08-20 23:20:33 - INFO - [3d9610ba-18fc-4512-876c-62775d568781] 30 frames saved to temp_videos/3d9610ba-18fc-4512-876c-62775d568781 |
|
2025-08-20 23:20:34 - INFO - Prompt token length: 3604 |
|
2025-08-20 23:20:53 - INFO - Tokens per second: 43.20754976197641, Peak GPU memory MB: 9378.375 |
|
2025-08-20 23:20:53 - INFO - [3d9610ba-18fc-4512-876c-62775d568781] Inference time: 24.83 seconds, CPU usage: 38.8%, CPU core utilization: [20.3, 39.8, 19.5, 75.4] |
|
2025-08-20 23:20:53 - INFO - [3d9610ba-18fc-4512-876c-62775d568781] Cleaned up temporary frame directory: temp_videos/3d9610ba-18fc-4512-876c-62775d568781 |
|
2025-08-20 23:20:53 - INFO - [91f8f3d5-15de-406b-834c-7aa4204cb5de] Received new video inference request. Prompt: 'Please describe the video in detail, only focus on customer and staff behavior and activities and do not overly describe the static scene.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_002.mp4' |
|
2025-08-20 23:20:53 - INFO - [91f8f3d5-15de-406b-834c-7aa4204cb5de] Video saved to temporary file: temp_videos/91f8f3d5-15de-406b-834c-7aa4204cb5de.mp4 |
|
2025-08-20 23:20:53 - INFO - [91f8f3d5-15de-406b-834c-7aa4204cb5de] Extracting frames using method: uniform, rate/threshold: 30 |
|
2025-08-20 23:20:58 - INFO - [91f8f3d5-15de-406b-834c-7aa4204cb5de] Extracted 30 frames successfully. Saving to temporary files... |
|
2025-08-20 23:20:58 - INFO - [91f8f3d5-15de-406b-834c-7aa4204cb5de] 30 frames saved to temp_videos/91f8f3d5-15de-406b-834c-7aa4204cb5de |
|
2025-08-20 23:20:58 - INFO - Prompt token length: 3604 |
|
2025-08-20 23:21:21 - INFO - Tokens per second: 38.828257610417374, Peak GPU memory MB: 9378.375 |
|
2025-08-20 23:21:21 - INFO - [91f8f3d5-15de-406b-834c-7aa4204cb5de] Inference time: 27.69 seconds, CPU usage: 54.6%, CPU core utilization: [46.3, 65.5, 40.6, 66.1] |
|
2025-08-20 23:21:21 - INFO - [91f8f3d5-15de-406b-834c-7aa4204cb5de] Cleaned up temporary frame directory: temp_videos/91f8f3d5-15de-406b-834c-7aa4204cb5de |
|
2025-08-20 23:21:21 - INFO - [9f1dd041-e69e-4183-8efa-f61fd08559c2] Received new video inference request. Prompt: 'Please describe the video in detail, only focus on customer and staff behavior and activities and do not overly describe the static scene.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_002.mp4' |
|
2025-08-20 23:21:21 - INFO - [9f1dd041-e69e-4183-8efa-f61fd08559c2] Video saved to temporary file: temp_videos/9f1dd041-e69e-4183-8efa-f61fd08559c2.mp4 |
|
2025-08-20 23:21:21 - INFO - [9f1dd041-e69e-4183-8efa-f61fd08559c2] Extracting frames using method: uniform, rate/threshold: 30 |
|
2025-08-20 23:21:29 - INFO - [9f1dd041-e69e-4183-8efa-f61fd08559c2] Extracted 30 frames successfully. Saving to temporary files... |
|
2025-08-20 23:21:29 - INFO - [9f1dd041-e69e-4183-8efa-f61fd08559c2] 30 frames saved to temp_videos/9f1dd041-e69e-4183-8efa-f61fd08559c2 |
|
2025-08-20 23:21:29 - INFO - Prompt token length: 3604 |
|
2025-08-20 23:21:51 - INFO - Tokens per second: 43.03845068270847, Peak GPU memory MB: 9378.375 |
|
2025-08-20 23:21:51 - INFO - [9f1dd041-e69e-4183-8efa-f61fd08559c2] Inference time: 29.71 seconds, CPU usage: 53.7%, CPU core utilization: [39.4, 55.5, 81.5, 38.5] |
|
2025-08-20 23:21:51 - INFO - [9f1dd041-e69e-4183-8efa-f61fd08559c2] Cleaned up temporary frame directory: temp_videos/9f1dd041-e69e-4183-8efa-f61fd08559c2 |
|
2025-08-20 23:21:51 - INFO - [827dbb61-d685-495c-883d-067090aa9e49] Received new video inference request. Prompt: 'Please describe the video in detail, only focus on customer and staff behavior and activities and do not overly describe the static scene.', Video: '/mnt/data/xiuying/Code/local_deploy/video/Clips_60s/sample_part_003.mp4' |
|
2025-08-20 23:21:51 - INFO - [827dbb61-d685-495c-883d-067090aa9e49] Video saved to temporary file: temp_videos/827dbb61-d685-495c-883d-067090aa9e49.mp4 |
|
2025-08-20 23:21:51 - INFO - [827dbb61-d685-495c-883d-067090aa9e49] Extracting frames using method: uniform, rate/threshold: 30 |
|
2025-08-20 23:21:56 - INFO - [827dbb61-d685-495c-883d-067090aa9e49] Extracted 30 frames successfully. Saving to temporary files... |
|
2025-08-20 23:21:56 - INFO - [827dbb61-d685-495c-883d-067090aa9e49] 30 frames saved to temp_videos/827dbb61-d685-495c-883d-067090aa9e49 |
|
2025-08-20 23:21:56 - INFO - Prompt token length: 3604 |
|
2025-08-20 23:22:13 - INFO - Tokens per second: 43.19212817813234, Peak GPU memory MB: 9378.375 |
|
2025-08-20 23:22:13 - INFO - [827dbb61-d685-495c-883d-067090aa9e49] Inference time: 22.10 seconds, CPU usage: 40.3%, CPU core utilization: [22.0, 88.1, 21.6, 29.3] |
|
2025-08-20 23:22:13 - INFO - [827dbb61-d685-495c-883d-067090aa9e49] Cleaned up temporary frame directory: temp_videos/827dbb61-d685-495c-883d-067090aa9e49 |
|
|