Wangtwohappy's picture
Upload folder using huggingface_hub
f8ba0eb verified
2025-08-21 01:32:07 - INFO - Loading model: Qwen/Qwen2-VL-2B-Instruct-AWQ
2025-08-21 01:32:11 - 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).
2025-08-21 01:32:38 - INFO - Model loaded in 31.45 seconds
2025-08-21 01:32:38 - INFO - GPU Memory Usage after model load: 2369.47 MB
2025-08-21 01:32:48 - INFO - [6806d96b-50d0-41d5-8703-320d06e1bb84] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/new/Clips_60s/video_part_001.mp4'
2025-08-21 01:32:48 - INFO - [6806d96b-50d0-41d5-8703-320d06e1bb84] Video saved to temporary file: temp_videos/6806d96b-50d0-41d5-8703-320d06e1bb84.mp4
2025-08-21 01:32:48 - INFO - [6806d96b-50d0-41d5-8703-320d06e1bb84] Extracting frames using method: uniform, rate/threshold: 30
2025-08-21 01:32:52 - INFO - [6806d96b-50d0-41d5-8703-320d06e1bb84] Extracted 30 frames successfully. Saving to temporary files...
2025-08-21 01:32:52 - INFO - [6806d96b-50d0-41d5-8703-320d06e1bb84] 30 frames saved to temp_videos/6806d96b-50d0-41d5-8703-320d06e1bb84
2025-08-21 01:32:52 - INFO - Prompt token length: 2306
2025-08-21 01:33:04 - INFO - Tokens per second: 14.857358494588418, Peak GPU memory MB: 4514.375
2025-08-21 01:33:04 - INFO - [6806d96b-50d0-41d5-8703-320d06e1bb84] Inference time: 15.50 seconds, CPU usage: 32.9%, CPU core utilization: [32.8, 28.6, 29.2, 41.1]
2025-08-21 01:33:04 - INFO - [6806d96b-50d0-41d5-8703-320d06e1bb84] Cleaned up temporary frame directory: temp_videos/6806d96b-50d0-41d5-8703-320d06e1bb84
2025-08-21 01:33:04 - INFO - [5cb2e558-a2e2-4495-b40b-5f785967226f] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/new/Clips_60s/video_part_002.mp4'
2025-08-21 01:33:04 - INFO - [5cb2e558-a2e2-4495-b40b-5f785967226f] Video saved to temporary file: temp_videos/5cb2e558-a2e2-4495-b40b-5f785967226f.mp4
2025-08-21 01:33:04 - INFO - [5cb2e558-a2e2-4495-b40b-5f785967226f] Extracting frames using method: uniform, rate/threshold: 30
2025-08-21 01:33:07 - INFO - [5cb2e558-a2e2-4495-b40b-5f785967226f] Extracted 30 frames successfully. Saving to temporary files...
2025-08-21 01:33:07 - INFO - [5cb2e558-a2e2-4495-b40b-5f785967226f] 30 frames saved to temp_videos/5cb2e558-a2e2-4495-b40b-5f785967226f
2025-08-21 01:33:08 - INFO - Prompt token length: 2306
2025-08-21 01:33:17 - INFO - Tokens per second: 14.913712045394723, Peak GPU memory MB: 4514.375
2025-08-21 01:33:17 - INFO - [5cb2e558-a2e2-4495-b40b-5f785967226f] Inference time: 12.93 seconds, CPU usage: 42.1%, CPU core utilization: [24.8, 42.8, 25.7, 75.0]
2025-08-21 01:33:17 - INFO - [5cb2e558-a2e2-4495-b40b-5f785967226f] Cleaned up temporary frame directory: temp_videos/5cb2e558-a2e2-4495-b40b-5f785967226f
2025-08-21 01:33:17 - INFO - [515f2d40-6c02-40e7-b489-254d66061d58] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/new/Clips_60s/video_part_003.mp4'
2025-08-21 01:33:17 - INFO - [515f2d40-6c02-40e7-b489-254d66061d58] Video saved to temporary file: temp_videos/515f2d40-6c02-40e7-b489-254d66061d58.mp4
2025-08-21 01:33:17 - INFO - [515f2d40-6c02-40e7-b489-254d66061d58] Extracting frames using method: uniform, rate/threshold: 30
2025-08-21 01:33:20 - INFO - [515f2d40-6c02-40e7-b489-254d66061d58] Extracted 30 frames successfully. Saving to temporary files...
2025-08-21 01:33:20 - INFO - [515f2d40-6c02-40e7-b489-254d66061d58] 30 frames saved to temp_videos/515f2d40-6c02-40e7-b489-254d66061d58
2025-08-21 01:33:20 - INFO - Prompt token length: 2306
2025-08-21 01:33:39 - INFO - Tokens per second: 15.212866049846783, Peak GPU memory MB: 4514.375
2025-08-21 01:33:39 - INFO - [515f2d40-6c02-40e7-b489-254d66061d58] Inference time: 22.18 seconds, CPU usage: 35.0%, CPU core utilization: [28.2, 14.0, 81.7, 16.0]
2025-08-21 01:33:39 - INFO - [515f2d40-6c02-40e7-b489-254d66061d58] Cleaned up temporary frame directory: temp_videos/515f2d40-6c02-40e7-b489-254d66061d58
2025-08-21 01:33:39 - INFO - [7702f18f-4562-4928-bacd-861b024219c1] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/new/Clips_60s/video_part_004.mp4'
2025-08-21 01:33:39 - INFO - [7702f18f-4562-4928-bacd-861b024219c1] Video saved to temporary file: temp_videos/7702f18f-4562-4928-bacd-861b024219c1.mp4
2025-08-21 01:33:39 - INFO - [7702f18f-4562-4928-bacd-861b024219c1] Extracting frames using method: uniform, rate/threshold: 30
2025-08-21 01:33:43 - INFO - [7702f18f-4562-4928-bacd-861b024219c1] Extracted 30 frames successfully. Saving to temporary files...
2025-08-21 01:33:43 - INFO - [7702f18f-4562-4928-bacd-861b024219c1] 30 frames saved to temp_videos/7702f18f-4562-4928-bacd-861b024219c1
2025-08-21 01:33:43 - INFO - Prompt token length: 2306
2025-08-21 01:33:51 - INFO - Tokens per second: 14.729804011346738, Peak GPU memory MB: 4514.375
2025-08-21 01:33:51 - INFO - [7702f18f-4562-4928-bacd-861b024219c1] Inference time: 11.51 seconds, CPU usage: 44.6%, CPU core utilization: [43.6, 28.0, 27.7, 78.9]
2025-08-21 01:33:51 - INFO - [7702f18f-4562-4928-bacd-861b024219c1] Cleaned up temporary frame directory: temp_videos/7702f18f-4562-4928-bacd-861b024219c1
2025-08-21 01:33:51 - INFO - [14252659-b5fb-4fa7-8d3e-f62a3c69679b] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/new/Clips_60s/video_part_005.mp4'
2025-08-21 01:33:51 - INFO - [14252659-b5fb-4fa7-8d3e-f62a3c69679b] Video saved to temporary file: temp_videos/14252659-b5fb-4fa7-8d3e-f62a3c69679b.mp4
2025-08-21 01:33:51 - INFO - [14252659-b5fb-4fa7-8d3e-f62a3c69679b] Extracting frames using method: uniform, rate/threshold: 30
2025-08-21 01:33:54 - INFO - [14252659-b5fb-4fa7-8d3e-f62a3c69679b] Extracted 30 frames successfully. Saving to temporary files...
2025-08-21 01:33:54 - INFO - [14252659-b5fb-4fa7-8d3e-f62a3c69679b] 30 frames saved to temp_videos/14252659-b5fb-4fa7-8d3e-f62a3c69679b
2025-08-21 01:33:54 - INFO - Prompt token length: 2306
2025-08-21 01:34:03 - INFO - Tokens per second: 15.087484052694805, Peak GPU memory MB: 4514.375
2025-08-21 01:34:03 - INFO - [14252659-b5fb-4fa7-8d3e-f62a3c69679b] Inference time: 12.10 seconds, CPU usage: 41.3%, CPU core utilization: [37.5, 35.4, 68.2, 24.2]
2025-08-21 01:34:03 - INFO - [14252659-b5fb-4fa7-8d3e-f62a3c69679b] Cleaned up temporary frame directory: temp_videos/14252659-b5fb-4fa7-8d3e-f62a3c69679b
2025-08-21 01:34:03 - INFO - [f08308a4-d0e5-4d3f-ade5-4a3517c11659] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/new/Clips_60s/video_part_006.mp4'
2025-08-21 01:34:03 - INFO - [f08308a4-d0e5-4d3f-ade5-4a3517c11659] Video saved to temporary file: temp_videos/f08308a4-d0e5-4d3f-ade5-4a3517c11659.mp4
2025-08-21 01:34:03 - INFO - [f08308a4-d0e5-4d3f-ade5-4a3517c11659] Extracting frames using method: uniform, rate/threshold: 30
2025-08-21 01:34:06 - INFO - [f08308a4-d0e5-4d3f-ade5-4a3517c11659] Extracted 30 frames successfully. Saving to temporary files...
2025-08-21 01:34:06 - INFO - [f08308a4-d0e5-4d3f-ade5-4a3517c11659] 30 frames saved to temp_videos/f08308a4-d0e5-4d3f-ade5-4a3517c11659
2025-08-21 01:34:06 - INFO - Prompt token length: 2306
2025-08-21 01:34:17 - INFO - Tokens per second: 14.952252033094313, Peak GPU memory MB: 4514.375
2025-08-21 01:34:17 - INFO - [f08308a4-d0e5-4d3f-ade5-4a3517c11659] Inference time: 14.60 seconds, CPU usage: 40.3%, CPU core utilization: [21.8, 22.2, 22.3, 94.7]
2025-08-21 01:34:17 - INFO - [f08308a4-d0e5-4d3f-ade5-4a3517c11659] Cleaned up temporary frame directory: temp_videos/f08308a4-d0e5-4d3f-ade5-4a3517c11659
2025-08-21 01:34:17 - INFO - [5671a395-356d-43ae-9464-5fc071986b0e] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/new/Clips_60s/video_part_007.mp4'
2025-08-21 01:34:17 - INFO - [5671a395-356d-43ae-9464-5fc071986b0e] Video saved to temporary file: temp_videos/5671a395-356d-43ae-9464-5fc071986b0e.mp4
2025-08-21 01:34:17 - INFO - [5671a395-356d-43ae-9464-5fc071986b0e] Extracting frames using method: uniform, rate/threshold: 30
2025-08-21 01:34:21 - INFO - [5671a395-356d-43ae-9464-5fc071986b0e] Extracted 30 frames successfully. Saving to temporary files...
2025-08-21 01:34:21 - INFO - [5671a395-356d-43ae-9464-5fc071986b0e] 30 frames saved to temp_videos/5671a395-356d-43ae-9464-5fc071986b0e
2025-08-21 01:34:21 - INFO - Prompt token length: 2306
2025-08-21 01:34:29 - INFO - Tokens per second: 14.96244510342586, Peak GPU memory MB: 4514.375
2025-08-21 01:34:29 - INFO - [5671a395-356d-43ae-9464-5fc071986b0e] Inference time: 11.52 seconds, CPU usage: 42.8%, CPU core utilization: [33.2, 59.1, 33.1, 46.1]
2025-08-21 01:34:29 - INFO - [5671a395-356d-43ae-9464-5fc071986b0e] Cleaned up temporary frame directory: temp_videos/5671a395-356d-43ae-9464-5fc071986b0e
2025-08-21 01:34:29 - INFO - [09f8c5e5-7851-4ff6-85c5-fd9a0ad9d11f] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/new/Clips_60s/video_part_008.mp4'
2025-08-21 01:34:29 - INFO - [09f8c5e5-7851-4ff6-85c5-fd9a0ad9d11f] Video saved to temporary file: temp_videos/09f8c5e5-7851-4ff6-85c5-fd9a0ad9d11f.mp4
2025-08-21 01:34:29 - INFO - [09f8c5e5-7851-4ff6-85c5-fd9a0ad9d11f] Extracting frames using method: uniform, rate/threshold: 30
2025-08-21 01:34:32 - INFO - [09f8c5e5-7851-4ff6-85c5-fd9a0ad9d11f] Extracted 30 frames successfully. Saving to temporary files...
2025-08-21 01:34:32 - INFO - [09f8c5e5-7851-4ff6-85c5-fd9a0ad9d11f] 30 frames saved to temp_videos/09f8c5e5-7851-4ff6-85c5-fd9a0ad9d11f
2025-08-21 01:34:33 - INFO - Prompt token length: 2306
2025-08-21 01:34:43 - INFO - Tokens per second: 15.042997648777325, Peak GPU memory MB: 4514.375
2025-08-21 01:34:43 - INFO - [09f8c5e5-7851-4ff6-85c5-fd9a0ad9d11f] Inference time: 13.92 seconds, CPU usage: 40.3%, CPU core utilization: [35.6, 54.7, 22.9, 47.8]
2025-08-21 01:34:43 - INFO - [09f8c5e5-7851-4ff6-85c5-fd9a0ad9d11f] Cleaned up temporary frame directory: temp_videos/09f8c5e5-7851-4ff6-85c5-fd9a0ad9d11f
2025-08-21 01:34:43 - INFO - [9110b0b9-0870-40fe-bfa9-fde4a5519eeb] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/new/Clips_60s/video_part_009.mp4'
2025-08-21 01:34:43 - INFO - [9110b0b9-0870-40fe-bfa9-fde4a5519eeb] Video saved to temporary file: temp_videos/9110b0b9-0870-40fe-bfa9-fde4a5519eeb.mp4
2025-08-21 01:34:43 - INFO - [9110b0b9-0870-40fe-bfa9-fde4a5519eeb] Extracting frames using method: uniform, rate/threshold: 30
2025-08-21 01:34:46 - INFO - [9110b0b9-0870-40fe-bfa9-fde4a5519eeb] Extracted 30 frames successfully. Saving to temporary files...
2025-08-21 01:34:46 - INFO - [9110b0b9-0870-40fe-bfa9-fde4a5519eeb] 30 frames saved to temp_videos/9110b0b9-0870-40fe-bfa9-fde4a5519eeb
2025-08-21 01:34:46 - INFO - Prompt token length: 2306
2025-08-21 01:35:05 - INFO - Tokens per second: 15.022627137863786, Peak GPU memory MB: 4514.375
2025-08-21 01:35:05 - INFO - [9110b0b9-0870-40fe-bfa9-fde4a5519eeb] Inference time: 22.48 seconds, CPU usage: 35.1%, CPU core utilization: [14.0, 57.8, 15.6, 53.2]
2025-08-21 01:35:05 - INFO - [9110b0b9-0870-40fe-bfa9-fde4a5519eeb] Cleaned up temporary frame directory: temp_videos/9110b0b9-0870-40fe-bfa9-fde4a5519eeb
2025-08-21 01:35:05 - INFO - [a8af5915-754a-4c20-8eed-e7dc0e54633d] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/new/Clips_60s/video_part_010.mp4'
2025-08-21 01:35:05 - INFO - [a8af5915-754a-4c20-8eed-e7dc0e54633d] Video saved to temporary file: temp_videos/a8af5915-754a-4c20-8eed-e7dc0e54633d.mp4
2025-08-21 01:35:05 - INFO - [a8af5915-754a-4c20-8eed-e7dc0e54633d] Extracting frames using method: uniform, rate/threshold: 30
2025-08-21 01:35:09 - INFO - [a8af5915-754a-4c20-8eed-e7dc0e54633d] Extracted 30 frames successfully. Saving to temporary files...
2025-08-21 01:35:09 - INFO - [a8af5915-754a-4c20-8eed-e7dc0e54633d] 30 frames saved to temp_videos/a8af5915-754a-4c20-8eed-e7dc0e54633d
2025-08-21 01:35:09 - INFO - Prompt token length: 2306
2025-08-21 01:35:16 - INFO - Tokens per second: 14.923263484191663, Peak GPU memory MB: 4514.375
2025-08-21 01:35:16 - INFO - [a8af5915-754a-4c20-8eed-e7dc0e54633d] Inference time: 10.32 seconds, CPU usage: 45.6%, CPU core utilization: [35.4, 79.2, 32.6, 35.0]
2025-08-21 01:35:16 - INFO - [a8af5915-754a-4c20-8eed-e7dc0e54633d] Cleaned up temporary frame directory: temp_videos/a8af5915-754a-4c20-8eed-e7dc0e54633d
2025-08-21 01:35:16 - INFO - [a45614c0-df7a-4c35-a1ea-1efa6a29a8d8] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/new/Clips_60s/video_part_011.mp4'
2025-08-21 01:35:16 - INFO - [a45614c0-df7a-4c35-a1ea-1efa6a29a8d8] Video saved to temporary file: temp_videos/a45614c0-df7a-4c35-a1ea-1efa6a29a8d8.mp4
2025-08-21 01:35:16 - INFO - [a45614c0-df7a-4c35-a1ea-1efa6a29a8d8] Extracting frames using method: uniform, rate/threshold: 30
2025-08-21 01:35:19 - INFO - [a45614c0-df7a-4c35-a1ea-1efa6a29a8d8] Extracted 30 frames successfully. Saving to temporary files...
2025-08-21 01:35:19 - INFO - [a45614c0-df7a-4c35-a1ea-1efa6a29a8d8] 30 frames saved to temp_videos/a45614c0-df7a-4c35-a1ea-1efa6a29a8d8
2025-08-21 01:35:19 - INFO - Prompt token length: 2306
2025-08-21 01:35:27 - INFO - Tokens per second: 15.164410207215045, Peak GPU memory MB: 4514.375
2025-08-21 01:35:27 - INFO - [a45614c0-df7a-4c35-a1ea-1efa6a29a8d8] Inference time: 10.98 seconds, CPU usage: 44.3%, CPU core utilization: [88.7, 28.9, 33.2, 26.5]
2025-08-21 01:35:27 - INFO - [a45614c0-df7a-4c35-a1ea-1efa6a29a8d8] Cleaned up temporary frame directory: temp_videos/a45614c0-df7a-4c35-a1ea-1efa6a29a8d8
2025-08-21 01:35:27 - INFO - [8156334c-d671-4483-b468-863d84a26687] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/new/Clips_60s/video_part_012.mp4'
2025-08-21 01:35:27 - INFO - [8156334c-d671-4483-b468-863d84a26687] Video saved to temporary file: temp_videos/8156334c-d671-4483-b468-863d84a26687.mp4
2025-08-21 01:35:27 - INFO - [8156334c-d671-4483-b468-863d84a26687] Extracting frames using method: uniform, rate/threshold: 30
2025-08-21 01:35:30 - INFO - [8156334c-d671-4483-b468-863d84a26687] Extracted 30 frames successfully. Saving to temporary files...
2025-08-21 01:35:30 - INFO - [8156334c-d671-4483-b468-863d84a26687] 30 frames saved to temp_videos/8156334c-d671-4483-b468-863d84a26687
2025-08-21 01:35:30 - INFO - Prompt token length: 2306
2025-08-21 01:35:49 - INFO - Tokens per second: 15.117784722711388, Peak GPU memory MB: 4514.375
2025-08-21 01:35:49 - INFO - [8156334c-d671-4483-b468-863d84a26687] Inference time: 22.36 seconds, CPU usage: 34.6%, CPU core utilization: [24.1, 60.2, 15.1, 38.9]
2025-08-21 01:35:49 - INFO - [8156334c-d671-4483-b468-863d84a26687] Cleaned up temporary frame directory: temp_videos/8156334c-d671-4483-b468-863d84a26687
2025-08-21 01:35:49 - INFO - [58827a98-0a85-4ee4-8240-b10420154270] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/new/Clips_60s/video_part_013.mp4'
2025-08-21 01:35:49 - INFO - [58827a98-0a85-4ee4-8240-b10420154270] Video saved to temporary file: temp_videos/58827a98-0a85-4ee4-8240-b10420154270.mp4
2025-08-21 01:35:49 - INFO - [58827a98-0a85-4ee4-8240-b10420154270] Extracting frames using method: uniform, rate/threshold: 30
2025-08-21 01:35:52 - INFO - [58827a98-0a85-4ee4-8240-b10420154270] Extracted 30 frames successfully. Saving to temporary files...
2025-08-21 01:35:52 - INFO - [58827a98-0a85-4ee4-8240-b10420154270] 30 frames saved to temp_videos/58827a98-0a85-4ee4-8240-b10420154270
2025-08-21 01:35:53 - INFO - Prompt token length: 2306
2025-08-21 01:36:00 - INFO - Tokens per second: 14.985813897711381, Peak GPU memory MB: 4514.375
2025-08-21 01:36:00 - INFO - [58827a98-0a85-4ee4-8240-b10420154270] Inference time: 11.17 seconds, CPU usage: 41.0%, CPU core utilization: [25.1, 70.6, 23.8, 44.4]
2025-08-21 01:36:00 - INFO - [58827a98-0a85-4ee4-8240-b10420154270] Cleaned up temporary frame directory: temp_videos/58827a98-0a85-4ee4-8240-b10420154270
2025-08-21 01:36:00 - INFO - [cc8da7cb-4ffc-4400-a354-fe30fac0dc25] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/new/Clips_60s/video_part_014.mp4'
2025-08-21 01:36:00 - INFO - [cc8da7cb-4ffc-4400-a354-fe30fac0dc25] Video saved to temporary file: temp_videos/cc8da7cb-4ffc-4400-a354-fe30fac0dc25.mp4
2025-08-21 01:36:00 - INFO - [cc8da7cb-4ffc-4400-a354-fe30fac0dc25] Extracting frames using method: uniform, rate/threshold: 30
2025-08-21 01:36:04 - INFO - [cc8da7cb-4ffc-4400-a354-fe30fac0dc25] Extracted 30 frames successfully. Saving to temporary files...
2025-08-21 01:36:04 - INFO - [cc8da7cb-4ffc-4400-a354-fe30fac0dc25] 30 frames saved to temp_videos/cc8da7cb-4ffc-4400-a354-fe30fac0dc25
2025-08-21 01:36:04 - INFO - Prompt token length: 2306
2025-08-21 01:36:12 - INFO - Tokens per second: 15.019531662577604, Peak GPU memory MB: 4514.375
2025-08-21 01:36:12 - INFO - [cc8da7cb-4ffc-4400-a354-fe30fac0dc25] Inference time: 12.21 seconds, CPU usage: 40.9%, CPU core utilization: [58.5, 47.3, 33.7, 24.0]
2025-08-21 01:36:12 - INFO - [cc8da7cb-4ffc-4400-a354-fe30fac0dc25] Cleaned up temporary frame directory: temp_videos/cc8da7cb-4ffc-4400-a354-fe30fac0dc25
2025-08-21 01:36:12 - INFO - [95265fda-7544-4393-a928-5411d89f8f51] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/new/Clips_60s/video_part_015.mp4'
2025-08-21 01:36:12 - INFO - [95265fda-7544-4393-a928-5411d89f8f51] Video saved to temporary file: temp_videos/95265fda-7544-4393-a928-5411d89f8f51.mp4
2025-08-21 01:36:12 - INFO - [95265fda-7544-4393-a928-5411d89f8f51] Extracting frames using method: uniform, rate/threshold: 30
2025-08-21 01:36:16 - INFO - [95265fda-7544-4393-a928-5411d89f8f51] Extracted 30 frames successfully. Saving to temporary files...
2025-08-21 01:36:16 - INFO - [95265fda-7544-4393-a928-5411d89f8f51] 30 frames saved to temp_videos/95265fda-7544-4393-a928-5411d89f8f51
2025-08-21 01:36:16 - INFO - Prompt token length: 2306
2025-08-21 01:36:23 - INFO - Tokens per second: 14.90843712868291, Peak GPU memory MB: 4514.375
2025-08-21 01:36:23 - INFO - [95265fda-7544-4393-a928-5411d89f8f51] Inference time: 10.51 seconds, CPU usage: 42.4%, CPU core utilization: [33.2, 26.3, 25.8, 84.0]
2025-08-21 01:36:23 - INFO - [95265fda-7544-4393-a928-5411d89f8f51] Cleaned up temporary frame directory: temp_videos/95265fda-7544-4393-a928-5411d89f8f51
2025-08-21 01:36:23 - INFO - [5425fe3f-264e-4b86-b655-903ec4f4ef2e] Received new video inference request. Prompt: 'Summarize the key observable events in this 1-minute convenience store video clip. Focus strictly on the physical actions and interactions of the people. Describe only what you can see', Video: '/mnt/data/xiuying/Code/local_deploy/video/new/Clips_60s/video_part_016.mp4'
2025-08-21 01:36:23 - INFO - [5425fe3f-264e-4b86-b655-903ec4f4ef2e] Video saved to temporary file: temp_videos/5425fe3f-264e-4b86-b655-903ec4f4ef2e.mp4
2025-08-21 01:36:23 - INFO - [5425fe3f-264e-4b86-b655-903ec4f4ef2e] Extracting frames using method: uniform, rate/threshold: 30
2025-08-21 01:36:26 - INFO - [5425fe3f-264e-4b86-b655-903ec4f4ef2e] Extracted 30 frames successfully. Saving to temporary files...
2025-08-21 01:36:26 - INFO - [5425fe3f-264e-4b86-b655-903ec4f4ef2e] 30 frames saved to temp_videos/5425fe3f-264e-4b86-b655-903ec4f4ef2e
2025-08-21 01:36:27 - INFO - Prompt token length: 2306
2025-08-21 01:36:34 - INFO - Tokens per second: 15.01252738973886, Peak GPU memory MB: 4514.375
2025-08-21 01:36:34 - INFO - [5425fe3f-264e-4b86-b655-903ec4f4ef2e] Inference time: 11.52 seconds, CPU usage: 42.0%, CPU core utilization: [24.5, 25.9, 25.9, 91.7]
2025-08-21 01:36:34 - INFO - [5425fe3f-264e-4b86-b655-903ec4f4ef2e] Cleaned up temporary frame directory: temp_videos/5425fe3f-264e-4b86-b655-903ec4f4ef2e