{
  "source_file": "0930",
  "source_platform": "Dev.to",
  "author": "Julien Simon",
  "title_listed": "Deploying Llama3 with Inference Endpoints and AWS Inferentia2",
  "keywords": "",
  "domain": "大模型算法",
  "content_type": "深度技术解析",
  "is_paid_flag": "否",
  "url": "https://dev.to/juliensimon/deploying-llama3-with-inference-endpoints-and-aws-inferentia2-2bb9",
  "publish_date": "2024-05-24",
  "corpus_stage": "",
  "notes": "",
  "id": "0d96d5a3ae6d",
  "collected_at": "2026-10-02T14:00:58",
  "title": "Deploying Llama3 with Inference Endpoints and AWS Inferentia2 - DEV Community",
  "body_markdown": "In this video, I walk you through the simple process of deploying a Meta Llama 3 8B model with Hugging Face Inference Endpoints and the AWS Inferentia2 accelerator, first with the Hugging Face UI, then with the Hugging Face API.\nI use the latest version of the Hugging Face Text Generation Inference container and show you how to run streaming inference with the OpenAI client library. I also discuss Inferentia2 benchmarks.",
  "metadata": {
    "title": "Deploying Llama3 with Inference Endpoints and AWS Inferentia2 - DEV Community",
    "description": "In this video, I walk you through the simple process of deploying a Meta Llama 3 8B model with... Tagged with aws, mlops, transformers, huggingface.",
    "keywords": "aws, mlops, transformers, huggingface, software, coding, development, engineering, inclusive, community",
    "author": null,
    "og:type": "article",
    "og:url": "https://dev.to/juliensimon/deploying-llama3-with-inference-endpoints-and-aws-inferentia2-2bb9",
    "og:title": "Deploying Llama3 with Inference Endpoints and AWS Inferentia2",
    "og:description": "In this video, I walk you through the simple process of deploying a Meta Llama 3 8B model with...",
    "og:site_name": "DEV Community",
    "og:image": "https://media2.dev.to/dynamic/image/width=1000,height=500,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fxjp0996uyw3sye3wyfpk.png",
    "twitter:site": "@thepracticaldev",
    "twitter:creator": "@julsimon",
    "twitter:title": "Deploying Llama3 with Inference Endpoints and AWS Inferentia2",
    "twitter:description": "In this video, I walk you through the simple process of deploying a Meta Llama 3 8B model with...",
    "twitter:card": "summary_large_image",
    "twitter:widgets:new-embed-design": "on",
    "twitter:image:src": "https://media2.dev.to/dynamic/image/width=1000,height=500,fit=cover,gravity=auto,format=auto/https%3A%2F%2Fdev-to-uploads.s3.amazonaws.com%2Fuploads%2Farticles%2Fxjp0996uyw3sye3wyfpk.png"
  },
  "paywall": {
    "listed_paid": false,
    "detected": false,
    "marker": "",
    "public_only": false,
    "policy": "付费/会员内容只保留页面公开可见部分，不绕过付费墙"
  },
  "crawl": {
    "success": true,
    "status_code": 200,
    "error": ""
  },
  "code_blocks": [],
  "images": [
    {
      "status": "http_404",
      "url": "https://res.cloudinary.com/practicaldev/image/fetch/s--4GNcLjfg--/c_limit%2Cf_auto%2Cfl_progressive%2Cq_auto%2Cw_800/https://cdn-images-1.medium.com/max/945/1%2Au0Hu8NARSQGgnHIl10OCOQ.png",
      "src": "https://res.cloudinary.com/practicaldev/image/fetch/s--4GNcLjfg--/c_limit%2Cf_auto%2Cfl_progressive%2Cq_auto%2Cw_800/https://cdn-images-1.medium.com/max/945/1%2Au0Hu8NARSQGgnHIl10OCOQ.png",
      "alt": "",
      "downloaded": false,
      "retried_at": "2026-10-20T17:45:41Z"
    }
  ],
  "audio": [],
  "videos": [
    {
      "url": "https://www.youtube.com/watch?v=c2nNEK2xmh0",
      "src": "https://www.youtube.com/embed/c2nNEK2xmh0",
      "status": "ok",
      "kind": "single_video",
      "local_path": "attachments/0d96d5a3ae6d/videos/repair-c2nNEK2xmh0.mp4",
      "bytes": 44778976,
      "valid": true,
      "height": 1080,
      "width": 1920,
      "duration": "606.501000",
      "reused": false
    }
  ],
  "links": [
    {
      "href": "https://res.cloudinary.com/practicaldev/image/fetch/s--4GNcLjfg--/c_limit%2Cf_auto%2Cfl_progressive%2Cq_auto%2Cw_800/https://cdn-images-1.medium.com/max/945/1%2Au0Hu8NARSQGgnHIl10OCOQ.png",
      "label": "",
      "type": "a"
    },
    {
      "href": "https://www.youtube.com/embed/c2nNEK2xmh0",
      "label": "",
      "type": "iframe"
    }
  ],
  "repair_version": 2,
  "repaired_at": "2026-10-14T10:49:05Z",
  "source_url": "https://dev.to/juliensimon/deploying-llama3-with-inference-endpoints-and-aws-inferentia2-2bb9",
  "papers": [],
  "actual_video_files": [],
  "body_chars": 424,
  "expected_body_images": 1,
  "discovery_status": "ok",
  "delivery_status": "partial",
  "missing_reason": "http_404",
  "raw_html": "attachments/0d96d5a3ae6d/pages/source.html",
  "local_html": "attachments/0d96d5a3ae6d/pages/article.html",
  "body_base_path": "attachments/0d96d5a3ae6d/pages/",
  "body_markdown_path": "attachments/0d96d5a3ae6d/pages/article.md"
}