{"id":31725567,"url":"https://github.com/cmpark0126/llm-vlm-cpp-onnx-inference","last_synced_at":"2025-10-09T05:50:31.331Z","repository":{"id":317163876,"uuid":"1061794507","full_name":"cmpark0126/llm-vlm-cpp-onnx-inference","owner":"cmpark0126","description":"LLM/VLM ONNX 모델의 C++ 텍스트 생성 애플리케이션 개발, Static Graph 추출 및 TTFT/TPOT 성능 측정","archived":false,"fork":false,"pushed_at":"2025-09-29T08:06:28.000Z","size":222,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":0,"default_branch":"main","last_synced_at":"2025-09-29T10:08:19.497Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"language":"C++","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/cmpark0126.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-09-22T11:50:26.000Z","updated_at":"2025-09-29T08:06:32.000Z","dependencies_parsed_at":"2025-09-30T00:03:54.319Z","dependency_job_id":null,"html_url":"https://github.com/cmpark0126/llm-vlm-cpp-onnx-inference","commit_stats":null,"previous_names":["cmpark0126/llm-vlm-cpp-onnx-inference"],"tags_count":null,"template":false,"template_full_name":null,"purl":"pkg:github/cmpark0126/llm-vlm-cpp-onnx-inference","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cmpark0126%2Fllm-vlm-cpp-onnx-inference","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cmpark0126%2Fllm-vlm-cpp-onnx-inference/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cmpark0126%2Fllm-vlm-cpp-onnx-inference/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cmpark0126%2Fllm-vlm-cpp-onnx-inference/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/cmpark0126","download_url":"https://codeload.github.com/cmpark0126/llm-vlm-cpp-onnx-inference/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/cmpark0126%2Fllm-vlm-cpp-onnx-inference/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":279000747,"owners_count":26082932,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-10-09T02:00:07.460Z","response_time":59,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-10-09T05:50:30.332Z","updated_at":"2025-10-09T05:50:31.325Z","avatar_url":"https://github.com/cmpark0126.png","language":"C++","funding_links":[],"categories":[],"sub_categories":[],"readme":"# LLM/VLM C++ ONNX Inference\n\n- 모든 동작은 AWS의 `Ubuntu Server 24.04 LTS (HVM),EBS General Purpose (SSD) Volume Type.` Amazon Machine Image, `t2.2xlarge` Instance Type, 60GiB Storage 환경을 기준으로 합니다.\n- Docker가 설치되어 있고, 16GiB 메모리, 60GiB Storage가 확보되는 경우에는 MAC이나 다른 환경에서도 동작 가능할 것으로 예상되나, 제대로 테스트되지는 않았습니다.\n\n## AWS EC2 기준 Docker Container 환경 준비\n```bash\nsudo apt-get update\nsudo apt-get install docker.io\ngit clone https://github.com/cmpark0126/llm-vlm-cpp-onnx-inference.git\ncd llm-vlm-cpp-onnx-inference\nsudo docker build -t llm-vlm-dev .\nsudo docker run --name llm-vlm-dev -v $(pwd):/workspace --memory=\"16g\" --shm-size=\"8g\" -it llm-vlm-dev\n$ ... # 컨테이너 내부 자동 진입, 호스트 파일 변경 실시간 반영\n```\n\n## 사전 작업 및 과제 실행\nDocker 컨테이너 내에서:\n```bash\n# 예제 허깅페이스 레포 다운로드 (문제1, 3)\n./setup.sh\n\n# Hugging Face 토큰 설정 (문제 2)\n# 사전에 gemma-3-1b-it 활용 허가를 받은 token이어야 함\nexport HF_TOKEN=your_huggingface_token_here\n\n# 각 문제는 ./run.sh 를 실행하면 (1) python baseline 코드를 실행하고, (2) 이후 C++ 구현을 실행하도록 구성되어 있다.\n\n# 문제 1: LLM 텍스트 생성\ncd problem1-llm\n./run.sh\ncd ..\n\n# 문제 2: Static graph export \u0026 텍스트 생성\ncd problem2-static\n./run.sh\ncd ..\n\n# 문제 3: VLM 텍스트 생성\ncd problem3-vlm\n./run.sh\ncd ..\n```\n\n## 결과 리포트\n- [REPORT.md](./REPORT.md)\n\n## 컨테이너 종료 및 제거\n```bash\nsudo docker stop llm-vlm-dev \u0026\u0026 sudo docker rm llm-vlm-dev\n```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcmpark0126%2Fllm-vlm-cpp-onnx-inference","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fcmpark0126%2Fllm-vlm-cpp-onnx-inference","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fcmpark0126%2Fllm-vlm-cpp-onnx-inference/lists"}