{
  "$schema_doc": "https://gtmstacker.com/registry/schema/entry.schema.json",
  "stability": "emerging",
  "generator": "agentic-media-registry",
  "generated_at": "2026-10-10T00:00:00Z",
  "id": "com.gtmstacker.registry/tool/ml-drift",
  "type": "tool",
  "slug": "ml-drift",
  "canonical_url": "https://gtmstacker.com/registry/tool/ml-drift/",
  "title": "ML Drift",
  "description": "Google's open-source (Apache-2.0), cross-platform GPU-accelerated inference engine for on-device machine learning, succeeding the GPU backend inside TensorFlow Lite/LiteRT — runs AI/ML workloads on mobile, web, and desktop GPUs via OpenCL, Metal, WebGPU, and OpenGL ES.",
  "category": "ai-infrastructure",
  "tags": [
    "ai-infrastructure",
    "self-hostable",
    "on-device",
    "inference",
    "open-source"
  ],
  "status": "active",
  "revision": 1,
  "content_hash": "c185ba1dfb218f2e2557a2dbe072a6ec36b97f8493cb6d637e514cd63598ceaf",
  "date_published": "2026-10-10T00:00:00Z",
  "date_modified": "2026-10-10T00:00:00Z",
  "source": {
    "name": "github · google-ai-edge/ml-drift",
    "url": "https://github.com/google-ai-edge/ml-drift"
  },
  "license": "Apache-2.0",
  "one_liner": "ML Drift is Google's open-source GPU engine that runs on-device AI inference on mobile, web, and desktop without a server round-trip.",
  "open_source": "yes",
  "self_hostable": "yes",
  "pricing_model": "free",
  "who_its_for": "A team shipping AI features into a mobile app, browser extension, or desktop client who wants inference to run on the user's own device GPU instead of a metered API call, for latency, cost, or privacy reasons.",
  "who_its_not_for": "Teams running large models server-side where device-GPU constraints don't apply — ML Drift targets on-device inference, not datacenter-scale serving.",
  "aliases": [
    "ML Drift",
    "MLDrift",
    "LiteRT GPU accelerator"
  ],
  "alternatives": [],
  "secondary_categories": [],
  "last_verified": "2026-10-10",
  "evidence": {
    "claim_type": "vendor-claim",
    "source_id": "https://github.com/google-ai-edge/ml-drift",
    "note": "Apache-2.0, 117 stars, 12 forks — WebFetch-verified 2026-10-10. Supports OpenCL, Metal, WebGPU (via Dawn), and OpenGL ES 3.1+; integrates as LiteRT's GPU accelerator. Google's own engineering-blog numbers (up to 40% latency cut on YouTube Shorts, up to 2s faster Google Photos) are the vendor's internal production results, not independently reproduced here."
  },
  "caveats": "Very new standalone open-source release (117 stars) even though the underlying tech has been running in Google products for years — expect the external developer experience and docs to mature. Reported performance gains are Google's own internal production numbers, not independently benchmarked.",
  "lead": "Google's open-source, cross-platform GPU-accelerated inference engine for on-device machine learning — the same GPU backend that has powered TensorFlow Lite/LiteRT inside Google products, now published as a standalone Apache-2.0 repo. Runs AI/ML workloads, including large generative models, on mobile, web, and desktop GPUs via OpenCL, Metal, WebGPU, and OpenGL ES 3.1+.",
  "chunks": [
    {
      "index": 0,
      "heading_path": [],
      "est_tokens": 93,
      "text": "Google's open-source, cross-platform GPU-accelerated inference engine for on-device machine learning — the same GPU backend that has powered TensorFlow Lite/LiteRT inside Google products, now published as a standalone Apache-2.0 repo. Runs AI/ML workloads, including large generative models, on mobile, web, and desktop GPUs via OpenCL, Metal, WebGPU, and OpenGL ES 3.1+."
    },
    {
      "index": 1,
      "heading_path": [
        null,
        "Provenance"
      ],
      "est_tokens": 169,
      "text": "open-source, cross-platform GPU-accelerated inference engine for on-device machine learning — the same GPU backend that has powered TensorFlow Lite/LiteRT inside Google products, now published as a standalone Apache-2.0 repo. Runs AI/ML workloads, including large generative models, on mobile, web, and desktop GPUs via OpenCL, Metal, WebGPU, and OpenGL ES 3.1+.\n\n- Apache-2.0, 117 stars, 12 forks — independently WebFetch-verified 2026-10-10 (github.com/google-ai-edge/ml-drift).\n- Surfaced via the 2026-10-10 OSS X pull (Google AI Edge team announcement thread).\n- Curated from the GTM Stacker signal registry (2026-10-10 pass); license independently verified 2026-10-10."
    },
    {
      "index": 2,
      "heading_path": [
        null,
        "Why it matters for a GTM stack"
      ],
      "est_tokens": 269,
      "text": "- Apache-2.0, 117 stars, 12 forks — independently WebFetch-verified 2026-10-10 (github.com/google-ai-edge/ml-drift).\n- Surfaced via the 2026-10-10 OSS X pull (Google AI Edge team announcement thread).\n- Curated from the GTM Stacker signal registry (2026-10-10 pass); license independently verified 2026-10-10.\n\nShipping an AI feature into a consumer-facing app usually means a metered API call per inference, which adds latency, cost, and a data round-trip a privacy-sensitive user or team may not want. ML Drift's bet is that the device GPU already sitting in the user's phone or browser can do real inference work for free, if the engine abstracts away the OpenCL/Metal/WebGPU/OpenGL differences. The honest read: this is Google's internal GPU backend newly published standalone, so the headline performance numbers (up to 40% latency cut, up to 2 seconds faster) are Google's own production results on Google's own products, not independently re-verified on a general third-party app — worth prototyping on your actual model and device mix before assuming the same gains."
    }
  ],
  "alternates": {
    "markdown": "https://gtmstacker.com/registry/tool/ml-drift/index.md",
    "html": "https://gtmstacker.com/registry/tool/ml-drift/",
    "json": "https://gtmstacker.com/registry/tool/ml-drift/index.json",
    "server_json": "https://gtmstacker.com/registry/tool/ml-drift/server.json"
  },
  "jsonld": {
    "@context": "https://schema.org",
    "@graph": [
      {
        "@type": "WebSite",
        "@id": "https://gtmstacker.com/#website",
        "url": "https://gtmstacker.com/",
        "name": "GTM Stacker Agent Registry",
        "description": "A daily-updated, agent-native registry of open-source tool discoveries, tool updates, and curated news for the go-to-market / RevOps engineering niche. Machine-readable first: agents can discover, parse, page, and delta-sync it without scraping HTML.",
        "inLanguage": "en",
        "publisher": {
          "@id": "https://gtmstacker.com/#organization"
        }
      },
      {
        "@type": "Organization",
        "@id": "https://gtmstacker.com/#organization",
        "name": "GTM Stacker",
        "url": "https://gtmstacker.com",
        "description": "The growth-systems practice of Theo Popov: AI-native enrichment, outbound, content engines and internal tooling for startups and venture programs. Its agent-native media property, the GTM Stacker Agent Registry, maintains a daily-updated catalog of open-source go-to-market and RevOps tools that both people and AI engines can discover, compare, and cite.",
        "foundingDate": "2024-08",
        "knowsAbout": [
          "go-to-market engineering",
          "RevOps",
          "sales automation",
          "marketing operations",
          "open-source software",
          "AI agents"
        ],
        "founder": {
          "@type": "Person",
          "@id": "https://gtmstacker.com/#founder",
          "name": "Theo Popov",
          "jobTitle": "Growth Operations & GTM Systems",
          "url": "https://gtmstacker.com/about/",
          "sameAs": [
            "https://www.linkedin.com/in/theo-popov",
            "https://x.com/Theo_Popov",
            "https://github.com/theopopov"
          ],
          "worksFor": {
            "@id": "https://gtmstacker.com/#organization"
          }
        },
        "sameAs": [
          "https://www.linkedin.com/company/gtmstacker",
          "https://www.youtube.com/@gtmstacker",
          "https://www.instagram.com/gtmstacker/",
          "https://www.tiktok.com/@gtmstacker"
        ],
        "mainEntityOfPage": "https://gtmstacker.com/registry/about/"
      },
      {
        "@type": "SoftwareApplication",
        "@id": "https://gtmstacker.com/registry/tool/ml-drift/#software",
        "name": "ML Drift",
        "identifier": "io.github.google-ai-edge/ml-drift",
        "description": "Google's open-source (Apache-2.0), cross-platform GPU-accelerated inference engine for on-device machine learning, succeeding the GPU backend inside TensorFlow Lite/LiteRT — runs AI/ML workloads on mobile, web, and desktop GPUs via OpenCL, Metal, WebGPU, and OpenGL ES.",
        "applicationCategory": "DeveloperApplication",
        "url": "https://gtmstacker.com/registry/tool/ml-drift/",
        "datePublished": "2026-10-10T00:00:00Z",
        "dateModified": "2026-10-10T00:00:00Z",
        "isPartOf": {
          "@id": "https://gtmstacker.com/#website"
        },
        "license": "https://spdx.org/licenses/Apache-2.0.html",
        "codeRepository": "https://github.com/google-ai-edge/ml-drift",
        "keywords": "ai-infrastructure, self-hostable, on-device, inference, open-source",
        "author": {
          "@type": "Organization",
          "name": "google-ai-edge",
          "url": "https://github.com/google-ai-edge",
          "sameAs": [
            "https://github.com/google-ai-edge/ml-drift"
          ]
        },
        "offers": {
          "@type": "Offer",
          "price": 0,
          "priceCurrency": "USD"
        }
      },
      {
        "@type": "BreadcrumbList",
        "@id": "https://gtmstacker.com/registry/tool/ml-drift/#breadcrumb",
        "itemListElement": [
          {
            "@type": "ListItem",
            "position": 1,
            "name": "GTM Stacker Registry",
            "item": "https://gtmstacker.com/registry/"
          },
          {
            "@type": "ListItem",
            "position": 2,
            "name": "AI Infrastructure",
            "item": "https://gtmstacker.com/registry/category/ai-infrastructure/"
          },
          {
            "@type": "ListItem",
            "position": 3,
            "name": "ML Drift",
            "item": "https://gtmstacker.com/registry/tool/ml-drift/"
          }
        ]
      }
    ]
  },
  "tool": {
    "name": "io.github.google-ai-edge/ml-drift",
    "repository": {
      "url": "https://github.com/google-ai-edge/ml-drift",
      "source": "github"
    }
  }
}