{
    "componentChunkName": "component---src-templates-post-tsx",
    "path": "/kernl/",
    "result": {"data":{"logo":null,"markdownRemark":{"html":"<h1>Sooftware Serving - Kernl</h1>\n<p><a href=\"https://github.com/ELS-RD\">ELS-RD (Lefebvre Dalloz Services)</a> 라는 단체에서 <a href=\"https://github.com/ELS-RD/kernl\">Kernl</a> 이라는 좋은\nInference Enginer을 내주었습니다! PyTorch 기반의 Transformer 모델들의 인퍼런스를 최적화해주는 라이브러리입니다.\n<a href=\"https://openai.com/blog/triton/\">Open AI Triton</a> 기반으로 짜여져 있다고 하네요.</p>\n<img src=\"https://github.com/ELS-RD/kernl/raw/main/resources/images/speedup.png\" width=\"550\">\n<p>위 그림을 보면, 상당히 빨라 보입니다. 많이 쓰이는 ONNX보다는 모든 상황에서 더 빠르고, TensorRT나 DeepSpeed와 비교했을 때는\n상황에 따라 엎치락뒤치락 하는 것 같습니다.</p>\n<p>애증의 TensorRT라고 부를 정도로, 속도는 빠르지만 환경설정이 어렵기로 유명한데, 이 라이브러리가 적절한\n대안이 됐으면 좋겠네요.</p>\n<h2>Usage</h2>\n<div class=\"gatsby-highlight\" data-language=\"python\"><pre class=\"language-python\"><code class=\"language-python\"><span class=\"token keyword\">import</span> torch\n<span class=\"token keyword\">from</span> transformers <span class=\"token keyword\">import</span> AutoModel\n<span class=\"token keyword\">from</span> kernl<span class=\"token punctuation\">.</span>model_optimization <span class=\"token keyword\">import</span> optimize_model\n\nmodel <span class=\"token operator\">=</span> AutoModel<span class=\"token punctuation\">.</span>from_pretrained<span class=\"token punctuation\">(</span>model_name<span class=\"token punctuation\">)</span><span class=\"token punctuation\">.</span><span class=\"token builtin\">eval</span><span class=\"token punctuation\">(</span><span class=\"token punctuation\">)</span><span class=\"token punctuation\">.</span>cuda<span class=\"token punctuation\">(</span><span class=\"token punctuation\">)</span>\noptimized_model <span class=\"token operator\">=</span> optimize_model<span class=\"token punctuation\">(</span>model<span class=\"token punctuation\">)</span>\n\ninputs <span class=\"token operator\">=</span> <span class=\"token punctuation\">.</span><span class=\"token punctuation\">.</span><span class=\"token punctuation\">.</span>\n\n<span class=\"token keyword\">with</span> torch<span class=\"token punctuation\">.</span>inference_mode<span class=\"token punctuation\">(</span><span class=\"token punctuation\">)</span><span class=\"token punctuation\">,</span> torch<span class=\"token punctuation\">.</span>cuda<span class=\"token punctuation\">.</span>amp<span class=\"token punctuation\">.</span>autocast<span class=\"token punctuation\">(</span><span class=\"token punctuation\">)</span><span class=\"token punctuation\">:</span>\n    outputs <span class=\"token operator\">=</span> optimized_model<span class=\"token punctuation\">(</span><span class=\"token operator\">**</span>inputs<span class=\"token punctuation\">)</span></code></pre></div>\n<p>위의 Usage를 보시다싶이, 사용법이 간단합니다.<br>\n많이들 쓰시는 Huggingface의 Transformers와 쉽게 연동되는 점이 큰 강점인 것 같네요.<br>\n또한 유저들이 편하게 커스터마이징 가능하도록 코드를 최대한 쉽고 짧게 짰다고 합니다.</p>\n<h2>Installation</h2>\n<div class=\"gatsby-highlight\" data-language=\"text\"><pre class=\"language-text\"><code class=\"language-text\">pip install torch==1.12.1 -U --extra-index-url https://download.pytorch.org/whl/cu116\ngit clone https://github.com/ELS-RD/kernl &amp;&amp; cd kernl\npip install -e .</code></pre></div>\n<p>설치 커맨드입니다. 주의사항으로, 파이썬 3.9 이상의 버젼만 지원된다고 합니다.</p>\n<h2>Reference</h2>\n<ul>\n<li>Kernl: <a href=\"https://github.com/ELS-RD/kernl\">https://github.com/ELS-RD/kernl</a></li>\n<li>ELS-RD: <a href=\"https://github.com/ELS-RD\">https://github.com/ELS-RD</a></li>\n<li>Open AI Triton: <a href=\"https://openai.com/blog/triton/\">https://openai.com/blog/triton/</a></li>\n</ul>","htmlAst":{"type":"root","children":[{"type":"element","tagName":"h1","properties":{},"children":[{"type":"text","value":"Sooftware Serving - Kernl"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"element","tagName":"a","properties":{"href":"https://github.com/ELS-RD"},"children":[{"type":"text","value":"ELS-RD (Lefebvre Dalloz Services)"}]},{"type":"text","value":" 라는 단체에서 "},{"type":"element","tagName":"a","properties":{"href":"https://github.com/ELS-RD/kernl"},"children":[{"type":"text","value":"Kernl"}]},{"type":"text","value":" 이라는 좋은\nInference Enginer을 내주었습니다! PyTorch 기반의 Transformer 모델들의 인퍼런스를 최적화해주는 라이브러리입니다.\n"},{"type":"element","tagName":"a","properties":{"href":"https://openai.com/blog/triton/"},"children":[{"type":"text","value":"Open AI Triton"}]},{"type":"text","value":" 기반으로 짜여져 있다고 하네요."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"img","properties":{"src":"https://github.com/ELS-RD/kernl/raw/main/resources/images/speedup.png","width":550},"children":[]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"위 그림을 보면, 상당히 빨라 보입니다. 많이 쓰이는 ONNX보다는 모든 상황에서 더 빠르고, TensorRT나 DeepSpeed와 비교했을 때는\n상황에 따라 엎치락뒤치락 하는 것 같습니다."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"애증의 TensorRT라고 부를 정도로, 속도는 빠르지만 환경설정이 어렵기로 유명한데, 이 라이브러리가 적절한\n대안이 됐으면 좋겠네요."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"Usage"}]},{"type":"text","value":"\n"},{"type":"element","tagName":"div","properties":{"className":["gatsby-highlight"],"dataLanguage":"python"},"children":[{"type":"element","tagName":"pre","properties":{"className":["language-python"]},"children":[{"type":"element","tagName":"code","properties":{"className":["language-python"]},"children":[{"type":"element","tagName":"span","properties":{"className":["token","keyword"]},"children":[{"type":"text","value":"import"}]},{"type":"text","value":" torch\n"},{"type":"element","tagName":"span","properties":{"className":["token","keyword"]},"children":[{"type":"text","value":"from"}]},{"type":"text","value":" transformers "},{"type":"element","tagName":"span","properties":{"className":["token","keyword"]},"children":[{"type":"text","value":"import"}]},{"type":"text","value":" AutoModel\n"},{"type":"element","tagName":"span","properties":{"className":["token","keyword"]},"children":[{"type":"text","value":"from"}]},{"type":"text","value":" kernl"},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":"."}]},{"type":"text","value":"model_optimization "},{"type":"element","tagName":"span","properties":{"className":["token","keyword"]},"children":[{"type":"text","value":"import"}]},{"type":"text","value":" optimize_model\n\nmodel "},{"type":"element","tagName":"span","properties":{"className":["token","operator"]},"children":[{"type":"text","value":"="}]},{"type":"text","value":" AutoModel"},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":"."}]},{"type":"text","value":"from_pretrained"},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":"("}]},{"type":"text","value":"model_name"},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":")"}]},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":"."}]},{"type":"element","tagName":"span","properties":{"className":["token","builtin"]},"children":[{"type":"text","value":"eval"}]},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":"("}]},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":")"}]},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":"."}]},{"type":"text","value":"cuda"},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":"("}]},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":")"}]},{"type":"text","value":"\noptimized_model "},{"type":"element","tagName":"span","properties":{"className":["token","operator"]},"children":[{"type":"text","value":"="}]},{"type":"text","value":" optimize_model"},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":"("}]},{"type":"text","value":"model"},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":")"}]},{"type":"text","value":"\n\ninputs "},{"type":"element","tagName":"span","properties":{"className":["token","operator"]},"children":[{"type":"text","value":"="}]},{"type":"text","value":" "},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":"."}]},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":"."}]},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":"."}]},{"type":"text","value":"\n\n"},{"type":"element","tagName":"span","properties":{"className":["token","keyword"]},"children":[{"type":"text","value":"with"}]},{"type":"text","value":" torch"},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":"."}]},{"type":"text","value":"inference_mode"},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":"("}]},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":")"}]},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":","}]},{"type":"text","value":" torch"},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":"."}]},{"type":"text","value":"cuda"},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":"."}]},{"type":"text","value":"amp"},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":"."}]},{"type":"text","value":"autocast"},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":"("}]},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":")"}]},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":":"}]},{"type":"text","value":"\n    outputs "},{"type":"element","tagName":"span","properties":{"className":["token","operator"]},"children":[{"type":"text","value":"="}]},{"type":"text","value":" optimized_model"},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":"("}]},{"type":"element","tagName":"span","properties":{"className":["token","operator"]},"children":[{"type":"text","value":"**"}]},{"type":"text","value":"inputs"},{"type":"element","tagName":"span","properties":{"className":["token","punctuation"]},"children":[{"type":"text","value":")"}]}]}]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"위의 Usage를 보시다싶이, 사용법이 간단합니다."},{"type":"element","tagName":"br","properties":{},"children":[]},{"type":"text","value":"\n많이들 쓰시는 Huggingface의 Transformers와 쉽게 연동되는 점이 큰 강점인 것 같네요."},{"type":"element","tagName":"br","properties":{},"children":[]},{"type":"text","value":"\n또한 유저들이 편하게 커스터마이징 가능하도록 코드를 최대한 쉽고 짧게 짰다고 합니다."}]},{"type":"text","value":"\n"},{"type":"element","tagName":"h2","properties":{},"children":[{"type":"text","value":"Installation"}]},{"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":"pip install torch==1.12.1 -U --extra-index-url https://download.pytorch.org/whl/cu116\ngit clone https://github.com/ELS-RD/kernl && cd kernl\npip install -e ."}]}]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"p","properties":{},"children":[{"type":"text","value":"설치 커맨드입니다. 주의사항으로, 파이썬 3.9 이상의 버젼만 지원된다고 합니다."}]},{"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":"text","value":"Kernl: "},{"type":"element","tagName":"a","properties":{"href":"https://github.com/ELS-RD/kernl"},"children":[{"type":"text","value":"https://github.com/ELS-RD/kernl"}]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"ELS-RD: "},{"type":"element","tagName":"a","properties":{"href":"https://github.com/ELS-RD"},"children":[{"type":"text","value":"https://github.com/ELS-RD"}]}]},{"type":"text","value":"\n"},{"type":"element","tagName":"li","properties":{},"children":[{"type":"text","value":"Open AI Triton: "},{"type":"element","tagName":"a","properties":{"href":"https://openai.com/blog/triton/"},"children":[{"type":"text","value":"https://openai.com/blog/triton/"}]}]},{"type":"text","value":"\n"}]}],"data":{"quirksMode":false}},"excerpt":"Sooftware Serving - Kernl ELS-RD (Lefebvre Dalloz Services) 라는 단체에서 Kernl 이라는 좋은\nInference Enginer을 내주었습니다! PyTorch 기반의 Transformer…","fields":{"readingTime":{"text":"2 min read"}},"frontmatter":{"title":"Sooftware Serving - Kernl","userDate":"30 October 2022","date":"2022-10-30T15:11:55.000Z","tags":["nlp","serving"],"excerpt":null,"image":{"childImageSharp":{"gatsbyImageData":{"layout":"fullWidth","backgroundColor":"#f8f8f8","images":{"fallback":{"src":"/static/cc06dfef1b9fb501041f1a21c55352cd/9edb4/kernl.png","srcSet":"/static/cc06dfef1b9fb501041f1a21c55352cd/343d9/kernl.png 750w,\n/static/cc06dfef1b9fb501041f1a21c55352cd/9edb4/kernl.png 997w","sizes":"100vw"},"sources":[{"srcSet":"/static/cc06dfef1b9fb501041f1a21c55352cd/06f57/kernl.webp 750w,\n/static/cc06dfef1b9fb501041f1a21c55352cd/2da53/kernl.webp 997w","type":"image/webp","sizes":"100vw"}]},"width":1,"height":0.3761283851554664}}},"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":"/kernl/","prev":{"excerpt":"개인 운동 기록 - 2022.10.30 한 달하고 3주만의 기록이다. 안타깝게도, 수행능력은 이전 기록과 동일한 것 같다. 그래도 좋은 소식은\n한 달동안 근육량은 유지한채, 지방만 3kg정도 빠졌다. 1년 반동안 멈췄던 운동을 다시 시작하면서…","frontmatter":{"title":"[RECORD] 개인 운동 기록 - 2022.10.30","tags":["record"],"date":"2022-10-30T10:00:00.000Z","draft":false,"excerpt":null,"image":{"childImageSharp":{"gatsbyImageData":{"layout":"fullWidth","placeholder":{"fallback":"data:image/png;base64,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"},"images":{"fallback":{"src":"/static/b946d74ba30a0f569bd677b887e90add/20435/weight_training2.png","srcSet":"/static/b946d74ba30a0f569bd677b887e90add/ea847/weight_training2.png 750w,\n/static/b946d74ba30a0f569bd677b887e90add/4a806/weight_training2.png 1080w,\n/static/b946d74ba30a0f569bd677b887e90add/e2aad/weight_training2.png 1366w,\n/static/b946d74ba30a0f569bd677b887e90add/20435/weight_training2.png 1920w","sizes":"100vw"},"sources":[{"srcSet":"/static/b946d74ba30a0f569bd677b887e90add/57584/weight_training2.webp 750w,\n/static/b946d74ba30a0f569bd677b887e90add/984df/weight_training2.webp 1080w,\n/static/b946d74ba30a0f569bd677b887e90add/4a276/weight_training2.webp 1366w,\n/static/b946d74ba30a0f569bd677b887e90add/9c00f/weight_training2.webp 1920w","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":"2 min read"},"layout":"","slug":"/weight_training2/"}},"next":{"excerpt":"2022 인공지능 그랜드 챌린지 - 정책지원 3위 2022 인공지능 그랜드 챌린지 (정책 지원 AI)에서…","frontmatter":{"title":"2022 인공지능 그랜드 챌린지 (정책 지원 AI) 3위","tags":["record"],"date":"2022-12-30T10:00:00.000Z","draft":false,"excerpt":null,"image":{"childImageSharp":{"gatsbyImageData":{"layout":"fullWidth","placeholder":{"fallback":"data:image/png;base64,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"},"images":{"fallback":{"src":"/static/13a059d448dc3a3baa33bc643a7bf772/20435/img_1.png","srcSet":"/static/13a059d448dc3a3baa33bc643a7bf772/ea847/img_1.png 750w,\n/static/13a059d448dc3a3baa33bc643a7bf772/4a806/img_1.png 1080w,\n/static/13a059d448dc3a3baa33bc643a7bf772/e2aad/img_1.png 1366w,\n/static/13a059d448dc3a3baa33bc643a7bf772/20435/img_1.png 1920w","sizes":"100vw"},"sources":[{"srcSet":"/static/13a059d448dc3a3baa33bc643a7bf772/57584/img_1.webp 750w,\n/static/13a059d448dc3a3baa33bc643a7bf772/984df/img_1.webp 1080w,\n/static/13a059d448dc3a3baa33bc643a7bf772/4a276/img_1.webp 1366w,\n/static/13a059d448dc3a3baa33bc643a7bf772/9c00f/img_1.webp 1920w","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,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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":"2 min read"},"layout":"","slug":"/2022_ai_grand_challenge/"}},"primaryTag":"nlp"}},
    "staticQueryHashes": ["3170763342","3229353822"]}