inpaintServer/logs/main_server.log

208 lines
20 KiB
Plaintext
Raw Blame History

This file contains invisible Unicode characters

This file contains invisible Unicode characters that are indistinguishable to humans but may be processed differently by a computer. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.

INFO: Started server process [41241]
2025-08-29 21:56:12,908 - uvicorn.error - INFO - Started server process [41241]
INFO: Waiting for application startup.
2025-08-29 21:56:12,909 - uvicorn.error - INFO - Waiting for application startup.
2025-08-29 21:56:12,910 - main - INFO - 🚀 인페인팅 서버 시작 중...
2025-08-29 21:56:12,911 - main - INFO - ✅ 공유 객체를 app.state에 저장 완료
2025-08-29 21:56:12,911 - main - INFO - 🔄 상태 저장 백그라운드 작업 생성 중...
2025-08-29 21:56:12,911 - main - INFO - ✅ 상태 저장 백그라운드 작업 생성 완료
2025-08-29 21:56:12,912 - main - INFO - 🚀 세션 풀 초기화 (CUDA 자동 감지)
2025-08-29 21:56:12,912 - app.core.session_pool - INFO - Initializing session pools...
2025-08-29 21:56:12,912 - app.core.session_pool - INFO - Initializing 4 sessions for simple_lama
2025-08-29 21:56:16,159 - app.models.simple_lama - INFO - Loading Simple LAMA model...
2025-08-29 21:56:20,613 - app.models.simple_lama - INFO - 실제 SimpleLama 모델 로딩 완료
2025-08-29 21:56:20,614 - app.models.simple_lama - INFO - Simple LAMA model loaded successfully
2025-08-29 21:56:20,615 - app.core.session_pool - INFO - Simple LAMA 모델 세션 로드 완료
2025-08-29 21:56:20,616 - app.core.session_pool - INFO - Created session simple_lama_0
2025-08-29 21:56:20,617 - app.models.simple_lama - INFO - Loading Simple LAMA model...
2025-08-29 21:56:22,400 - app.models.simple_lama - INFO - 실제 SimpleLama 모델 로딩 완료
2025-08-29 21:56:22,401 - app.models.simple_lama - INFO - Simple LAMA model loaded successfully
2025-08-29 21:56:22,401 - app.core.session_pool - INFO - Simple LAMA 모델 세션 로드 완료
2025-08-29 21:56:22,402 - app.core.session_pool - INFO - Created session simple_lama_1
2025-08-29 21:56:22,402 - app.models.simple_lama - INFO - Loading Simple LAMA model...
2025-08-29 21:56:24,088 - app.models.simple_lama - INFO - 실제 SimpleLama 모델 로딩 완료
2025-08-29 21:56:24,088 - app.models.simple_lama - INFO - Simple LAMA model loaded successfully
2025-08-29 21:56:24,089 - app.core.session_pool - INFO - Simple LAMA 모델 세션 로드 완료
2025-08-29 21:56:24,089 - app.core.session_pool - INFO - Created session simple_lama_2
2025-08-29 21:56:24,089 - app.models.simple_lama - INFO - Loading Simple LAMA model...
2025-08-29 21:56:25,756 - app.models.simple_lama - INFO - 실제 SimpleLama 모델 로딩 완료
2025-08-29 21:56:25,756 - app.models.simple_lama - INFO - Simple LAMA model loaded successfully
2025-08-29 21:56:25,757 - app.core.session_pool - INFO - Simple LAMA 모델 세션 로드 완료
2025-08-29 21:56:25,757 - app.core.session_pool - INFO - Created session simple_lama_3
2025-08-29 21:56:25,757 - app.core.session_pool - INFO - Initializing 4 sessions for migan
2025-08-29 21:56:25,822 - app.models.migan - INFO - Loading MIGAN ONNX model...
2025-08-29 21:56:25,822 - app.models.migan - INFO - MIGAN ONNX 런타임 세션 생성 시도...
2025-08-29 21:56:25,823 - app.models.migan - INFO - MIGAN ONNX providers 설정: ['CUDAExecutionProvider', 'CPUExecutionProvider']
2025-08-29 21:56:27.238315022 [W:onnxruntime:, transformer_memcpy.cc:74 ApplyImpl] 17 Memcpy nodes are added to the graph main_graph for CUDAExecutionProvider. It might have negative impact on performance (including unable to run CUDA graph). Set session_options.log_severity_level=1 to see the detail logs before this message.
2025-08-29 21:56:28,580 - app.models.migan - INFO - MIGAN ONNX 세션 생성 완료. Providers: ['CUDAExecutionProvider', 'CPUExecutionProvider']
2025-08-29 21:56:28,581 - app.models.migan - INFO - MIGAN ONNX model loaded successfully
2025-08-29 21:56:28,581 - app.core.session_pool - INFO - MIGAN 모델 세션 로드 완료
2025-08-29 21:56:28,582 - app.core.session_pool - INFO - Created session migan_0
2025-08-29 21:56:28,582 - app.models.migan - INFO - Loading MIGAN ONNX model...
2025-08-29 21:56:28,583 - app.models.migan - INFO - MIGAN ONNX 런타임 세션 생성 시도...
2025-08-29 21:56:28,583 - app.models.migan - INFO - MIGAN ONNX providers 설정: ['CUDAExecutionProvider', 'CPUExecutionProvider']
2025-08-29 21:56:29.684943504 [W:onnxruntime:, transformer_memcpy.cc:74 ApplyImpl] 17 Memcpy nodes are added to the graph main_graph for CUDAExecutionProvider. It might have negative impact on performance (including unable to run CUDA graph). Set session_options.log_severity_level=1 to see the detail logs before this message.
2025-08-29 21:56:29,852 - app.models.migan - INFO - MIGAN ONNX 세션 생성 완료. Providers: ['CUDAExecutionProvider', 'CPUExecutionProvider']
2025-08-29 21:56:29,853 - app.models.migan - INFO - MIGAN ONNX model loaded successfully
2025-08-29 21:56:29,853 - app.core.session_pool - INFO - MIGAN 모델 세션 로드 완료
2025-08-29 21:56:29,854 - app.core.session_pool - INFO - Created session migan_1
2025-08-29 21:56:29,854 - app.models.migan - INFO - Loading MIGAN ONNX model...
2025-08-29 21:56:29,854 - app.models.migan - INFO - MIGAN ONNX 런타임 세션 생성 시도...
2025-08-29 21:56:29,855 - app.models.migan - INFO - MIGAN ONNX providers 설정: ['CUDAExecutionProvider', 'CPUExecutionProvider']
2025-08-29 21:56:30.907277353 [W:onnxruntime:, transformer_memcpy.cc:74 ApplyImpl] 17 Memcpy nodes are added to the graph main_graph for CUDAExecutionProvider. It might have negative impact on performance (including unable to run CUDA graph). Set session_options.log_severity_level=1 to see the detail logs before this message.
2025-08-29 21:56:31,072 - app.models.migan - INFO - MIGAN ONNX 세션 생성 완료. Providers: ['CUDAExecutionProvider', 'CPUExecutionProvider']
2025-08-29 21:56:31,072 - app.models.migan - INFO - MIGAN ONNX model loaded successfully
2025-08-29 21:56:31,073 - app.core.session_pool - INFO - MIGAN 모델 세션 로드 완료
2025-08-29 21:56:31,073 - app.core.session_pool - INFO - Created session migan_2
2025-08-29 21:56:31,074 - app.models.migan - INFO - Loading MIGAN ONNX model...
2025-08-29 21:56:31,074 - app.models.migan - INFO - MIGAN ONNX 런타임 세션 생성 시도...
2025-08-29 21:56:31,074 - app.models.migan - INFO - MIGAN ONNX providers 설정: ['CUDAExecutionProvider', 'CPUExecutionProvider']
2025-08-29 21:56:32.141164804 [W:onnxruntime:, transformer_memcpy.cc:74 ApplyImpl] 17 Memcpy nodes are added to the graph main_graph for CUDAExecutionProvider. It might have negative impact on performance (including unable to run CUDA graph). Set session_options.log_severity_level=1 to see the detail logs before this message.
2025-08-29 21:56:32,306 - app.models.migan - INFO - MIGAN ONNX 세션 생성 완료. Providers: ['CUDAExecutionProvider', 'CPUExecutionProvider']
2025-08-29 21:56:32,307 - app.models.migan - INFO - MIGAN ONNX model loaded successfully
2025-08-29 21:56:32,308 - app.core.session_pool - INFO - MIGAN 모델 세션 로드 완료
2025-08-29 21:56:32,308 - app.core.session_pool - INFO - Created session migan_3
2025-08-29 21:56:32,309 - app.core.session_pool - INFO - Initializing 3 sessions for rembg
2025-08-29 21:56:32,310 - app.models.rembg_model - INFO - Loading REMBG model (birefnet-general-lite)...
2025-08-29 21:56:34,333 - app.models.rembg_model - INFO - rembg 모듈 임포트 성공 (세션 생성은 지연 로딩)
2025-08-29 21:56:34,334 - app.models.rembg_model - INFO - 🔧 rembg 새 세션 생성 필요: birefnet-general-lite_cuda_True
2025-08-29 21:56:34,334 - app.models.rembg_model - WARNING - rembg.sessions import 실패, 기본 방식 사용
2025-08-29 21:56:34,335 - app.models.rembg_model - INFO - rembg 세션 생성 providers: ['CUDAExecutionProvider', 'CPUExecutionProvider']
2025-08-29 21:56:47,648 - app.models.rembg_model - INFO - ✅ rembg 'birefnet-general-lite' GPU 가속로 동작 (providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'])
2025-08-29 21:56:47,649 - app.models.rembg_model - INFO - REMBG model (birefnet-general-lite) loaded successfully
2025-08-29 21:56:47,650 - app.core.session_pool - INFO - REMBG 모델 세션 로드 완료
2025-08-29 21:56:47,650 - app.core.session_pool - INFO - Created session rembg_0
2025-08-29 21:56:47,651 - app.models.rembg_model - INFO - Loading REMBG model (birefnet-general-lite)...
2025-08-29 21:56:47,651 - app.models.rembg_model - INFO - rembg 모듈 임포트 성공 (세션 생성은 지연 로딩)
2025-08-29 21:56:47,651 - app.models.rembg_model - INFO - 🔧 rembg 새 세션 생성 필요: birefnet-general-lite_cuda_True
2025-08-29 21:56:47,652 - app.models.rembg_model - WARNING - rembg.sessions import 실패, 기본 방식 사용
2025-08-29 21:56:47,652 - app.models.rembg_model - INFO - rembg 세션 생성 providers: ['CUDAExecutionProvider', 'CPUExecutionProvider']
2025-08-29 21:57:00,508 - app.models.rembg_model - INFO - ✅ rembg 'birefnet-general-lite' GPU 가속로 동작 (providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'])
2025-08-29 21:57:00,509 - app.models.rembg_model - INFO - REMBG model (birefnet-general-lite) loaded successfully
2025-08-29 21:57:00,509 - app.core.session_pool - INFO - REMBG 모델 세션 로드 완료
2025-08-29 21:57:00,510 - app.core.session_pool - INFO - Created session rembg_1
2025-08-29 21:57:00,510 - app.models.rembg_model - INFO - Loading REMBG model (birefnet-general-lite)...
2025-08-29 21:57:00,511 - app.models.rembg_model - INFO - rembg 모듈 임포트 성공 (세션 생성은 지연 로딩)
2025-08-29 21:57:00,511 - app.models.rembg_model - INFO - 🔧 rembg 새 세션 생성 필요: birefnet-general-lite_cuda_True
2025-08-29 21:57:00,512 - app.models.rembg_model - WARNING - rembg.sessions import 실패, 기본 방식 사용
2025-08-29 21:57:00,512 - app.models.rembg_model - INFO - rembg 세션 생성 providers: ['CUDAExecutionProvider', 'CPUExecutionProvider']
2025-08-29 21:57:13,223 - app.models.rembg_model - INFO - ✅ rembg 'birefnet-general-lite' GPU 가속로 동작 (providers: ['CUDAExecutionProvider', 'CPUExecutionProvider'])
2025-08-29 21:57:13,223 - app.models.rembg_model - INFO - REMBG model (birefnet-general-lite) loaded successfully
2025-08-29 21:57:13,224 - app.core.session_pool - INFO - REMBG 모델 세션 로드 완료
2025-08-29 21:57:13,224 - app.core.session_pool - INFO - Created session rembg_2
2025-08-29 21:57:13,225 - app.core.session_pool - INFO - Session pools initialized successfully
2025-08-29 21:57:13,225 - main - INFO - ✅ 세션 풀 초기화 완료
2025-08-29 21:57:13,225 - app.core.worker_manager - INFO - Starting worker manager...
2025-08-29 21:57:13,226 - app.core.worker_manager - INFO - Worker manager started with 4 workers
2025-08-29 21:57:13,226 - main - INFO - ✅ 워커 매니저 시작 완료
2025-08-29 21:57:13,227 - main - INFO - 🎉 인페인팅 서버 시작 완료!
2025-08-29 21:57:13,227 - main - INFO - 🔄 상태 저장 백그라운드 작업 시작됨
INFO: Application startup complete.
2025-08-29 21:57:16,343 - uvicorn.error - INFO - Application startup complete.
INFO: Uvicorn running on http://0.0.0.0:8008 (Press CTRL+C to quit)
2025-08-29 21:57:16,353 - uvicorn.error - INFO - Uvicorn running on http://0.0.0.0:8008 (Press CTRL+C to quit)
INFO: 127.0.0.1:54262 - "GET /api/v1/health HTTP/1.1" 404 Not Found
INFO: 127.0.0.1:54274 - "GET /api/v1/health HTTP/1.1" 404 Not Found
INFO: 192.168.0.119:61112 - "GET /health HTTP/1.1" 200 OK
INFO: 192.168.0.119:61231 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 21:59:51,134 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 21:59:57,813 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 6.722s
INFO: 192.168.0.119:61232 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:61299 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:00:02,737 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:00:18,011 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 15.314s
INFO: 192.168.0.119:61300 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:61373 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:00:22,330 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:00:23,972 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 1.694s
INFO: 192.168.0.119:61374 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:61417 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:00:28,723 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:00:30,117 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 1.445s
INFO: 192.168.0.119:61418 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:61459 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:00:35,326 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:00:36,758 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 1.471s
INFO: 192.168.0.119:61462 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:61491 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:00:41,071 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:00:42,651 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 1.618s
INFO: 192.168.0.119:61492 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:61507 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:00:47,196 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:00:48,619 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 1.450s
INFO: 192.168.0.119:61508 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:61521 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:00:52,857 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:00:54,558 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 1.736s
INFO: 192.168.0.119:61522 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:61553 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:00:58,326 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:00:59,657 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 1.371s
INFO: 192.168.0.119:61554 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:61568 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:01:04,284 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:01:05,630 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 1.378s
INFO: 192.168.0.119:61569 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:61766 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:01:57,794 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:02:00,934 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 3.179s
INFO: 192.168.0.119:61767 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:61819 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:02:06,382 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:02:07,866 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 1.514s
INFO: 192.168.0.119:61820 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:61864 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:02:15,220 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:02:16,792 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 1.615s
INFO: 192.168.0.119:61876 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:61923 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:02:22,461 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:02:23,790 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 1.377s
INFO: 192.168.0.119:61924 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:62164 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:03:01,528 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:03:04,020 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 2.532s
INFO: 192.168.0.119:62165 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:62225 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:03:13,341 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:03:15,572 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 2.260s
INFO: 192.168.0.119:62226 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:62291 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:03:21,500 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:03:29,405 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 7.941s
INFO: 192.168.0.119:62292 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:62546 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:04:02,266 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:04:12,367 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 10.139s
INFO: 192.168.0.119:62551 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:62613 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:04:16,160 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:04:18,086 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 1.959s
INFO: 192.168.0.119:62614 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:62653 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:04:23,356 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:04:25,222 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 1.918s
INFO: 192.168.0.119:62654 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:62769 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:04:49,806 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:04:51,747 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 1.978s
INFO: 192.168.0.119:62770 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: 192.168.0.119:62996 - "GET /api/v1/model HTTP/1.1" 200 OK
2025-08-29 22:05:37,916 - app.models.simple_lama - INFO - 실제 SimpleLama 모델로 인페인팅 수행
2025-08-29 22:05:41,193 - app.core.worker_manager - INFO - 'simple-lama' inpainting processed in 3.324s
INFO: Shutting down
2025-08-29 22:05:41,242 - uvicorn.error - INFO - Shutting down
INFO: 192.168.0.119:62998 - "POST /api/v1/inpaint HTTP/1.1" 200 OK
INFO: Waiting for application shutdown.
2025-08-29 22:05:41,344 - uvicorn.error - INFO - Waiting for application shutdown.
2025-08-29 22:05:41,345 - main - INFO - 🛑 인페인팅 서버 종료 중...
2025-08-29 22:05:41,345 - app.core.worker_manager - INFO - Stopping worker manager...
2025-08-29 22:05:41,346 - app.core.worker_manager - INFO - Worker manager stopped
2025-08-29 22:05:41,346 - main - INFO - ✅ 워커 매니저 중지 완료
2025-08-29 22:05:41,347 - main - INFO - 👋 인페인팅 서버 종료 완료
INFO: Application shutdown complete.
2025-08-29 22:05:41,347 - uvicorn.error - INFO - Application shutdown complete.
INFO: Finished server process [41241]
2025-08-29 22:05:41,348 - uvicorn.error - INFO - Finished server process [41241]