{
    "componentChunkName": "component---src-templates-post-tsx",
    "path": "/triton/",
    "result": {"data":{"logo":null,"markdownRemark":{"html":"<h1>Sooftware Serving - Triton Inference Server</h1>\n<ul>\n<li>Triton Inference Server는 인공지능 모델의 인퍼런스를 도와주는 오픈소스 소프트웨어다.</li>\n<li>다양한 프레임워크(TensorRT, TensorFlow, PyTorch ,ONNX, 등)를 지원한다.</li>\n<li>해당 내용은 <a href=\"https://github.com/triton-inference-server/server/tree/main/docs\">Triton Inference Server Docs</a> 를 공부하며 적은 내용으로,</li>\n</ul>\n<p>대부분의 내용이 해당 문서와 유사합니다.</p>\n<h2>Quickstart</h2>\n<p>Triton 사용시에는 pre-built 된 <a href=\"https://catalog.ngc.nvidia.com\">Docker image</a>를 사용하는게 좋다.<br>\n이번 Quickstart에서 다룰 내용:</p>\n<ul>\n<li>Creating a Model Repository</li>\n<li>Launching Triton</li>\n<li>Send an Inference Request</li>\n</ul>\n<h3>Model Repository</h3>\n<ul>\n<li>가장 먼저 Model Repository를 구성해야 한다.</li>\n<li>Model Repository에는 체크포인트와 입출력 configuration 파일이 포함되어야 한다.</li>\n<li><code class=\"language-text\">tritonserver --model-repository=경로</code>와 같이 실행할 때 경로를 지정해준다.</li>\n<li>Model Repository 구조</li>\n</ul>\n<div class=\"gatsby-highlight\" data-language=\"text\"><pre class=\"language-text\"><code class=\"language-text\">model_repository/\n    |\n    |___model1/\n    |     |___config.pbtxt\n    |     |___version/\n    |     |     |___model-files\n    |     |___version/\n    |     |     |___model-files\n    |     |___...\n    |___model2/\n    |     |___config.pbtxt\n    |     |___version/\n    |     |     |___model-files\n    |     |___version/\n    |     |     |___model-files\n    |     |___...\n    |___...</code></pre></div>\n<ul>\n<li>Model Repository 주의할\n<ul>\n<li>모델명 폴더 아래에 버젼으로 된 폴더가 존재해야한다. (버젼은 반드시 INT여야 함)</li>\n<li>버젼 폴더 아래에 모델의 체크포인트 및 관련 파일이 위치한다.</li>\n<li>모델 체크포인트는 <code class=\"language-text\">model.***</code>여야 한다. (***은 bin 등 플랫폼에 따라 상이)점</li>\n</ul>\n</li>\n</ul>\n<h2><code class=\"language-text\">config.pbtxt</code></h2>\n<ul>\n<li>모델 관련된 설정을 저장한다.</li>\n<li>트리톤 서버에서 이 정보를 기반으로 모델을 서빙한다.</li>\n<li>예시</li>\n</ul>\n<div class=\"gatsby-highlight\" data-language=\"text\"><pre class=\"language-text\"><code class=\"language-text\">name: \"simple\"\nplatform: \"tensorflow_graphdef\"\nmax_batch_size: 8\ninput [\n  {\n    name: \"INPUT0\"\n    data_type: TYPE_INT32\n    dims: [ 16 ]\n  },\n  {\n    name: \"INPUT1\"\n    data_type: TYPE_INT32\n    dims: [ 16 ]\n  }\n]\noutput [\n  {\n    name: \"OUTPUT0\"\n    data_type: TYPE_INT32\n    dims: [ 16 ]\n  },\n  {\n    name: \"OUTPUT1\"\n    data_type: TYPE_INT32\n    dims: [ 16 ]\n  }\n]</code></pre></div>\n<ul>\n<li>Parameters:\n<ul>\n<li><code class=\"language-text\">platform</code>: 모델 플랫폼 (tensorrt, onns, pytorch, tensorflow 등)</li>\n<li><code class=\"language-text\">max_batch_size</code>: 최대 배치사이즈</li>\n<li><code class=\"language-text\">input (list[dict])</code>: 입력 텐서들의 정보\n<ul>\n<li><code class=\"language-text\">name (str)</code>: 입력 이름</li>\n<li><code class=\"language-text\">data_type (enum)</code>: 타입 정보\n<ul>\n<li>타입정보는 <a href=\"https://github.com/triton-inference-server/server/blob/main/docs/model_configuration.md#datatypes\">https://github.com/triton-inference-server/server/blob/main/docs/model_configuration.md#datatypes</a> 여기서 확인.</li>\n</ul>\n</li>\n<li><code class=\"language-text\">dims (list[int])</code>: 텐서 쉐입\n<ul>\n<li>다이내믹 차원인 경우는 -1로 기록.</li>\n</ul>\n</li>\n</ul>\n</li>\n</ul>\n</li>\n<li><code class=\"language-text\">output</code>: 출력 텐서들의 정보\n<ul>\n<li>입력텐서와 동일한 구조이다.</li>\n</ul>\n</li>\n</ul>\n<h2>유용한 기능들</h2>\n<p>(작성중)</p>\n<h2>Reference</h2>\n<ul>\n<li><a href=\"https://github.com/triton-inference-server/server/tree/main/docs\">Triton Inference Server Docs</a></li>\n</ul>","htmlAst":{"type":"root","children":[{"type":"element","tagName":"h1","properties":{},"children":[{"type":"text","value":"Sooftware Serving - Triton Inference Server"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Triton Inference Server는 인공지능 모델의 인퍼런스를 도와주는 오픈소스 소프트웨어다."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"다양한 프레임워크(TensorRT, TensorFlow, PyTorch ,ONNX, 등)를 지원한다."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"해당 내용은 "},{"type":"element","tagName":"a","properties":{"href":"https://github.com/triton-inference-server/server/tree/main/docs"},"children":[{"type":"text","value":"Triton Inference Server Docs"}]},{"type":"text","value":" 를 공부하며 적은 내용으로,"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"대부분의 내용이 해당 문서와 유사합니다."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"Quickstart"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"Triton 사용시에는 pre-built 된 "},{"type":"element","tagName":"a","properties":{"href":"https://catalog.ngc.nvidia.com"},"children":[{"type":"text","value":"Docker image"}]},{"type":"text","value":"를 사용하는게 좋다."},{"type":"element","tagName":"br","properties":{},"children":[]},{"type":"text","value":"\n이번 Quickstart에서 다룰 내용:"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Creating a Model Repository"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Launching Triton"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Send an Inference Request"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h3","properties":{},"children":[{"type":"text","value":"Model Repository"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"가장 먼저 Model Repository를 구성해야 한다."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Model Repository에는 체크포인트와 입출력 configuration 파일이 포함되어야 한다."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"element","tagName":"code","properties":{"className":["language-text"]},"children":[{"type":"text","value":"tritonserver --model-repository=경로"}]},{"type":"text","value":"와 같이 실행할 때 경로를 지정해준다."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Model Repository 구조"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"div","properties":{"className":["gatsby-highlight"],"dataLanguage":"text"},"children":[{"type":"element","tagName":"pre","properties":{"className":["language-text"]},"children":[{"type":"element","tagName":"code","properties":{"className":["language-text"]},"children":[{"type":"text","value":"model_repository/\n    |\n    |___model1/\n    |     |___config.pbtxt\n    |     |___version/\n    |     |     |___model-files\n    |     |___version/\n    |     |     |___model-files\n    |     |___...\n    |___model2/\n    |     |___config.pbtxt\n    |     |___version/\n    |     |     |___model-files\n    |     |___version/\n    |     |     |___model-files\n    |     |___...\n    |___..."}]}]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Model Repository 주의할\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"모델명 폴더 아래에 버젼으로 된 폴더가 존재해야한다. (버젼은 반드시 INT여야 함)"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"버젼 폴더 아래에 모델의 체크포인트 및 관련 파일이 위치한다."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"모델 체크포인트는 "},{"type":"element","tagName":"code","properties":{"className":["language-text"]},"children":[{"type":"text","value":"model.***"}]},{"type":"text","value":"여야 한다. (***은 bin 등 플랫폼에 따라 상이)점"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"element","tagName":"code","properties":{"className":["language-text"]},"children":[{"type":"text","value":"config.pbtxt"}]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"모델 관련된 설정을 저장한다."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"트리톤 서버에서 이 정보를 기반으로 모델을 서빙한다."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"예시"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"div","properties":{"className":["gatsby-highlight"],"dataLanguage":"text"},"children":[{"type":"element","tagName":"pre","properties":{"className":["language-text"]},"children":[{"type":"element","tagName":"code","properties":{"className":["language-text"]},"children":[{"type":"text","value":"name: \"simple\"\nplatform: \"tensorflow_graphdef\"\nmax_batch_size: 8\ninput [\n  {\n    name: \"INPUT0\"\n    data_type: TYPE_INT32\n    dims: [ 16 ]\n  },\n  {\n    name: \"INPUT1\"\n    data_type: TYPE_INT32\n    dims: [ 16 ]\n  }\n]\noutput [\n  {\n    name: \"OUTPUT0\"\n    data_type: TYPE_INT32\n    dims: [ 16 ]\n  },\n  {\n    name: \"OUTPUT1\"\n    data_type: TYPE_INT32\n    dims: [ 16 ]\n  }\n]"}]}]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Parameters:\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"element","tagName":"code","properties":{"className":["language-text"]},"children":[{"type":"text","value":"platform"}]},{"type":"text","value":": 모델 플랫폼 (tensorrt, onns, pytorch, tensorflow 등)"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"element","tagName":"code","properties":{"className":["language-text"]},"children":[{"type":"text","value":"max_batch_size"}]},{"type":"text","value":": 최대 배치사이즈"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"element","tagName":"code","properties":{"className":["language-text"]},"children":[{"type":"text","value":"input (list[dict])"}]},{"type":"text","value":": 입력 텐서들의 정보\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"element","tagName":"code","properties":{"className":["language-text"]},"children":[{"type":"text","value":"name (str)"}]},{"type":"text","value":": 입력 이름"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"element","tagName":"code","properties":{"className":["language-text"]},"children":[{"type":"text","value":"data_type (enum)"}]},{"type":"text","value":": 타입 정보\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"타입정보는 "},{"type":"element","tagName":"a","properties":{"href":"https://github.com/triton-inference-server/server/blob/main/docs/model_configuration.md#datatypes"},"children":[{"type":"text","value":"https://github.com/triton-inference-server/server/blob/main/docs/model_configuration.md#datatypes"}]},{"type":"text","value":" 여기서 확인."}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"element","tagName":"code","properties":{"className":["language-text"]},"children":[{"type":"text","value":"dims (list[int])"}]},{"type":"text","value":": 텐서 쉐입\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"다이내믹 차원인 경우는 -1로 기록."}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"element","tagName":"code","properties":{"className":["language-text"]},"children":[{"type":"text","value":"output"}]},{"type":"text","value":": 출력 텐서들의 정보\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"입력텐서와 동일한 구조이다."}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"유용한 기능들"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"(작성중)"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"Reference"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"ul","properties":{},"children":[{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"element","tagName":"a","properties":{"href":"https://github.com/triton-inference-server/server/tree/main/docs"},"children":[{"type":"text","value":"Triton Inference Server Docs"}]}]},{"type":"text","value":"\n"}]}],"data":{"quirksMode":false}},"excerpt":"Sooftware Serving - Triton Inference Server Triton Inference Server는 인공지능 모델의 인퍼런스를 도와주는 오픈소스 소프트웨어다. 다양한 프레임워크(TensorRT, TensorFlow…","fields":{"readingTime":{"text":"3 min read"}},"frontmatter":{"title":"Sooftware Serving - Triton Inference Server","userDate":"20 September 2022","date":"2022-09-20T10:00:00.000Z","tags":["nlp","serving"],"excerpt":null,"image":{"childImageSharp":{"gatsbyImageData":{"layout":"fullWidth","backgroundColor":"#080808","images":{"fallback":{"src":"/static/2a825b8546ee78dfd77964613068ac58/60936/triton.png","srcSet":"/static/2a825b8546ee78dfd77964613068ac58/60936/triton.png 540w","sizes":"100vw"},"sources":[{"srcSet":"/static/2a825b8546ee78dfd77964613068ac58/1c40e/triton.webp 540w","type":"image/webp","sizes":"100vw"}]},"width":1,"height":0.5629629629629629}}},"author":[{"id":"Soohwan Kim","bio":"Co-founder/A.I. engineer at TUNiB.","avatar":{"children":[{"gatsbyImageData":{"layout":"fullWidth","backgroundColor":"#282838","images":{"fallback":{"src":"/static/a9e6b445142b247ee4cfa66155398bb2/0d6f4/soohwan.png","srcSet":"/static/a9e6b445142b247ee4cfa66155398bb2/248f9/soohwan.png 40w,\n/static/a9e6b445142b247ee4cfa66155398bb2/fd435/soohwan.png 80w,\n/static/a9e6b445142b247ee4cfa66155398bb2/0d6f4/soohwan.png 120w","sizes":"100vw"},"sources":[{"srcSet":"/static/a9e6b445142b247ee4cfa66155398bb2/e7f45/soohwan.webp 40w,\n/static/a9e6b445142b247ee4cfa66155398bb2/589ec/soohwan.webp 80w,\n/static/a9e6b445142b247ee4cfa66155398bb2/71a38/soohwan.webp 120w","type":"image/webp","sizes":"100vw"}]},"width":1,"height":0.6833333333333333}}]}}]}},"relatedPosts":{"totalCount":50,"edges":[{"node":{"id":"6529d72e-80e7-5d61-a672-d66276a3f641","excerpt":"MoE(Mixture of Experts) 기초부터 DeepSeek 혁신까지 작년 이맘때쯤 DeepSeek-V3가 저비용으로 엄청난 성능을 보이면서 화제가 되었습니다. 그 핵심 기술인 MoE(Mixture of Experts…","frontmatter":{"title":"MoE(Mixture of Experts) 기초부터 DeepSeek 혁신까지","date":"2026-01-15T01:11:55.000Z"},"fields":{"readingTime":{"text":"8 min read"},"slug":"/developed-moe/"}}},{"node":{"id":"8b49d3ef-4ce3-568c-9d71-240ff17fc3e0","excerpt":"BERT는 사실 Diffusion 모델이였다?! 최근 굉장히 흥미로운 글을 읽게되어 공유합니다. 원문 : link BERT와 Diffusion이 같은 방식이다?! NLP 연구자들에게 BERT는 너무 익숙한 모델입니다. 201…","frontmatter":{"title":"BERT는 사실 Diffusion 모델이였다?!","date":"2025-10-21T12:00:00.000Z"},"fields":{"readingTime":{"text":"8 min read"},"slug":"/bert_diffusion/"}}},{"node":{"id":"7c7e1676-ea84-58de-970c-ddec9aa10660","excerpt":"RLHF는 수다쟁이를 만든다?! (Does RLHF Breed Verbose Chatterboxes?!) RLHF(Reinforcement Learning from Human Feedback)는 OpenAI의 ChatGPT…","frontmatter":{"title":"RLHF는 수다쟁이를 만든다?! (Does RLHF Breed Verbose Chatterboxes?!)","date":"2024-03-13T01:11:55.000Z"},"fields":{"readingTime":{"text":"7 min read"},"slug":"/rlhf-vervosity/"}}},{"node":{"id":"2b9d3e22-1796-5fab-878d-5941d2e76e9d","excerpt":"LLM Paper Abstract - 2023.12 LLM…","frontmatter":{"title":"LLM Paper Abstract - 2023.12","date":"2024-01-05T10:00:00.000Z"},"fields":{"readingTime":{"text":"5 min read"},"slug":"/llm-abs-202312/"}}},{"node":{"id":"f43fa33b-917b-5c00-8462-937d99592ad7","excerpt":"What it MoE? (Mixture of Experts) 현존 최강 LLM인 GPT-4에서 “MoE (Mixture of Experts)” 방식을 채택하여 사용하고 있다고 알려졌는데요, 최근 AI계의 뜨거운 감자 Mistral AI…","frontmatter":{"title":"What is MoE? (Mixture of Experts)","date":"2023-12-22T01:11:55.000Z"},"fields":{"readingTime":{"text":"9 min read"},"slug":"/moe/"}}}]}},"pageContext":{"slug":"/triton/","prev":{"excerpt":"개인 운동 기록 - 2022.09.07 21살에 해병대 면접에 붙기 위해 팔굽혀펴기를 연습하던 때부터 전역 후 몇년간은 맨몸운동 위주의 운동을 꾸준히 했었는데,\n대학교…","frontmatter":{"title":"[RECORD] 개인 운동 기록 - 2022.09.07","tags":["record"],"date":"2022-09-07T10:00:00.000Z","draft":false,"excerpt":null,"image":{"childImageSharp":{"gatsbyImageData":{"layout":"fullWidth","placeholder":{"fallback":"data:image/png;base64,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"},"images":{"fallback":{"src":"/static/99465c8d8a87da139ff1a6a26fd298b3/4a806/weight_training.png","srcSet":"/static/99465c8d8a87da139ff1a6a26fd298b3/ea847/weight_training.png 750w,\n/static/99465c8d8a87da139ff1a6a26fd298b3/4a806/weight_training.png 1080w","sizes":"100vw"},"sources":[{"srcSet":"/static/99465c8d8a87da139ff1a6a26fd298b3/57584/weight_training.webp 750w,\n/static/99465c8d8a87da139ff1a6a26fd298b3/984df/weight_training.webp 1080w","type":"image/webp","sizes":"100vw"}]},"width":1,"height":0.6666666666666666}}},"author":[{"id":"Soohwan Kim","bio":"Co-founder/A.I. engineer at TUNiB.","avatar":{"childImageSharp":{"gatsbyImageData":{"layout":"fullWidth","placeholder":{"fallback":"data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABQAAAAOCAYAAAAvxDzwAAAACXBIWXMAABYlAAAWJQFJUiTwAAADjElEQVQ4y23Oy48TdQDA8TExEaTttvSBfdHddru7bWc6bWd+8+i0u23n0SdlBRQXZGHDgiiLDwgqXjCIJEaC8cLBmHgwUU9EYzRqQuLJi/4NJB6NF+8evgbOHr7XT76SM5ix7s4QnRHnnm9yZzvBTIswN8JcP5bC67ZoWi7CdtFsn5bloZo+dSNAMYbIIqCmD6mJIVXdR3J6I7r9IQ3T59pZlW+uxzndCbPdC/HZXoq3TikowsfqBOjOmFZ7SrM9p2kfRbXn1O0jKNbsSbJ5BMnu9Gl3+qiiz4OPSvz0QRLHFGwOZH6+neLHT5YRbRerM0J0JrTas/8FZXNKzZgg2es+ZtvDdbs8+iHJl+9lWVP7OG2br26k+PvXJCfmFqoYIpwhTXtMwxpTN0coxhjFmCKbE2rGmKoYPQY9qi2fyzsq//4e5sNXi5TlLqbd5t6lPH/9kuDTG2usqgGi7dO0hzSsIXUzQDaGKGKMLEZUxZCKCJB02+PUpMH9vQwP7ybYnSxyfNrjwumA3dEiD94v8cfnK7xzWsbpujQtH9X0qBs+iuEjC5+a7lPVPSqai9SyelyYFbjkh5hqC3TkKOutLON2nkYpgtuMcT6IszdPslo8SLlcpmUH1A0XRQyQhUtNuFQ1l4o2QFI1h3OTVXbcg+grIfSVBRqlEGopgrYSRi0e4KiIse1mScSeopA/iLADmoZL3Rgg631q+oCq1qeq95FOzhQefpzn7eMpBmqcoBVj04pzwkky0eNMRYIdL8F3twusLe2nslrE6g5pGX1U8/FhD1nvUW1tUJK7SH9+n+DR1zF2vQSvH0lz88wiV45V2J1WuHqsxLXNAnuzNJdfWmK5/BylUgFhb6DZAxR9g7rpIos+Wttja2uE9M9vYb69k+DqfJErWzLOuoVqdKlpDo4jODms4zlFckuHObx4iHwuRi6fYqmYY201x/LqMrnFDNl8gRvvukhNdT9394rcOlNFMxrUhYFmW9imTEsp0mhWKC2nWSokyWSiFA7HSKcXiEb34fayyLVniUQk8rmn2drKIqlqiNcuVrh2ymQS1Nh8sc/GoMEbl7u8eb5D1yqTzkRJJsOkkiGymQVShyLE4yHWKnEq1RjpTIhmI8r2y3mkyloI38uha1n6bpVXrkw5+4LD/S/2uHnrIopaJhZ9hmQqwqHkAXJP8BDhyD46ZoWdMxOGcx/PNfECk/8AbxXdRjRliPoAAAAASUVORK5CYII="},"images":{"fallback":{"src":"/static/a9e6b445142b247ee4cfa66155398bb2/7cf1f/soohwan.png","srcSet":"/static/a9e6b445142b247ee4cfa66155398bb2/34f77/soohwan.png 750w,\n/static/a9e6b445142b247ee4cfa66155398bb2/a94f6/soohwan.png 1080w,\n/static/a9e6b445142b247ee4cfa66155398bb2/7cf1f/soohwan.png 1148w","sizes":"100vw"},"sources":[{"srcSet":"/static/a9e6b445142b247ee4cfa66155398bb2/38420/soohwan.webp 750w,\n/static/a9e6b445142b247ee4cfa66155398bb2/7470d/soohwan.webp 1080w,\n/static/a9e6b445142b247ee4cfa66155398bb2/b5ef6/soohwan.webp 1148w","type":"image/webp","sizes":"100vw"}]},"width":1,"height":0.6829268292682927}}}}]},"fields":{"readingTime":{"text":"4 min read"},"layout":"","slug":"/weight_training1/"}},"next":{"excerpt":"Sooftware Serving - Terminology NLP…","frontmatter":{"title":"Sooftware Serving - Terminology","tags":["nlp","serving"],"date":"2022-10-04T10:00:00.000Z","draft":false,"excerpt":null,"image":{"childImageSharp":{"gatsbyImageData":{"layout":"fullWidth","placeholder":{"fallback":"data:image/png;base64,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"},"images":{"fallback":{"src":"/static/84b2e141b3f9a93f47a0cfa786f28c22/3ad85/term.png","srcSet":"/static/84b2e141b3f9a93f47a0cfa786f28c22/912f4/term.png 750w,\n/static/84b2e141b3f9a93f47a0cfa786f28c22/3ad85/term.png 900w","sizes":"100vw"},"sources":[{"srcSet":"/static/84b2e141b3f9a93f47a0cfa786f28c22/c23ad/term.webp 750w,\n/static/84b2e141b3f9a93f47a0cfa786f28c22/fc8e8/term.webp 900w","type":"image/webp","sizes":"100vw"}]},"width":1,"height":0.7744444444444445}}},"author":[{"id":"Soohwan Kim","bio":"Co-founder/A.I. engineer at TUNiB.","avatar":{"childImageSharp":{"gatsbyImageData":{"layout":"fullWidth","placeholder":{"fallback":"data:image/png;base64,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"},"images":{"fallback":{"src":"/static/a9e6b445142b247ee4cfa66155398bb2/7cf1f/soohwan.png","srcSet":"/static/a9e6b445142b247ee4cfa66155398bb2/34f77/soohwan.png 750w,\n/static/a9e6b445142b247ee4cfa66155398bb2/a94f6/soohwan.png 1080w,\n/static/a9e6b445142b247ee4cfa66155398bb2/7cf1f/soohwan.png 1148w","sizes":"100vw"},"sources":[{"srcSet":"/static/a9e6b445142b247ee4cfa66155398bb2/38420/soohwan.webp 750w,\n/static/a9e6b445142b247ee4cfa66155398bb2/7470d/soohwan.webp 1080w,\n/static/a9e6b445142b247ee4cfa66155398bb2/b5ef6/soohwan.webp 1148w","type":"image/webp","sizes":"100vw"}]},"width":1,"height":0.6829268292682927}}}}]},"fields":{"readingTime":{"text":"5 min read"},"layout":"","slug":"/serving_term/"}},"primaryTag":"nlp"}},
    "staticQueryHashes": ["3170763342","3229353822"]}