Skip to main content

TensorRT-LLM

This is the page you're already on — the Human View toggle above shows it in full.

A green key on the record, left, is one Decision Insights added. It doesn't exist on the company's site or in a wire feed. The same key labels its row on the right, so you can match them directly. More on how DI enriches a record.

The record

This is what the machine sees: the exact JSON-LD an agent receives for this listing.

WebSite
{
  "@context": "https://schema.org",
  "@id": "https://decisioninsights.ai/#website",
  "@type": "WebSite",
  "name": "Decision Insights",
  "potentialAction": {
    "@type": "SearchAction",
    "target": {
      "@type": "EntryPoint",
      "urlTemplate": "https://decisioninsights.ai/search/?q={search_term_string}\u0026submit=1"
    }
  },
  "publisher": {
    "@id": "https://decisioninsights.ai/#organization"
  },
  "url": "https://decisioninsights.ai"
}
Organization
{
  "@context": "https://schema.org",
  "@id": "https://decisioninsights.ai/#organization",
  "@type": "Organization",
  "contactPoint": {
    "@type": "ContactPoint",
    "contactType": "customer support",
    "email": "[email protected]"
  },
  "description": "Decision Insights is a Registry of technology companies, open source projects, and industry terms, built for people and for AI agents that need sourced, structured information.",
  "logo": {
    "@type": "ImageObject",
    "url": "https://wiretap-cdn-assets.nyc3.cdn.digitaloceanspaces.com/decision-insights/[email protected]"
  },
  "name": "Decision Insights",
  "parentOrganization": {
    "@type": "Organization",
    "name": "Wiretap Labs",
    "sameAs": [
      "https://www.linkedin.com/company/wiretap-labs",
      "https://www.crunchbase.com/organization/wiretap-labs"
    ],
    "url": "https://wiretaplabs.com"
  },
  "publishingPrinciples": "https://decisioninsights.ai/standards/",
  "sameAs": [
    "https://www.linkedin.com/company/decisioninsights"
  ],
  "url": "https://decisioninsights.ai"
}
BreadcrumbList
{
  "@context": "https://schema.org",
  "@type": "BreadcrumbList",
  "itemListElement": [
    {
      "@type": "ListItem",
      "item": "https://decisioninsights.ai",
      "name": "Decision Insights",
      "position": 1
    },
    {
      "@type": "ListItem",
      "item": "https://decisioninsights.ai/registry/",
      "name": "Registry",
      "position": 2
    },
    {
      "@type": "ListItem",
      "item": "https://decisioninsights.ai/projects/",
      "name": "Projects",
      "position": 3
    },
    {
      "@type": "ListItem",
      "item": "https://decisioninsights.ai/registry/nvidia-corp/",
      "name": "Nvidia",
      "position": 4
    },
    {
      "@type": "ListItem",
      "item": "https://decisioninsights.ai/projects/tensorrt-llm/",
      "name": "TensorRT-LLM",
      "position": 5
    }
  ]
}
SoftwareSourceCode
{
  "@context": "https://schema.org",
  "@id": "https://decisioninsights.ai/projects/tensorrt-llm/#project",
  "@type": "SoftwareSourceCode",
  "additionalProperty": [
    {
      "@type": "PropertyValue",
      "name": "Articles mentioning this entity",
      "value": 1
    },
    {
      "@type": "PropertyValue",
      "name": "Organizations named alongside this entity",
      "value": 9
    },
    {
      "@type": "PropertyValue",
      "name": "Related projects",
      "propertyID": "https://decisioninsights.ai/ns#relatedProjects",
      "value": [
        {
          "@id": "https://decisioninsights.ai/projects/tensorrt/#project",
          "@type": "SoftwareSourceCode",
          "mainEntityOfPage": "https://decisioninsights.ai/projects/tensorrt/",
          "name": "TensorRT"
        },
        {
          "@id": "https://decisioninsights.ai/projects/vllm/#project",
          "@type": "SoftwareSourceCode",
          "mainEntityOfPage": "https://decisioninsights.ai/projects/vllm/",
          "name": "vLLM"
        },
        {
          "@id": "https://decisioninsights.ai/projects/megatron-lm/#project",
          "@type": "SoftwareSourceCode",
          "mainEntityOfPage": "https://decisioninsights.ai/projects/megatron-lm/",
          "name": "Megatron-LM"
        },
        {
          "@id": "https://decisioninsights.ai/projects/openllm/#project",
          "@type": "SoftwareSourceCode",
          "mainEntityOfPage": "https://decisioninsights.ai/projects/openllm/",
          "name": "OpenLLM"
        },
        {
          "@id": "https://decisioninsights.ai/projects/mpt-mosaic-pretrained-transformer/#project",
          "@type": "SoftwareSourceCode",
          "mainEntityOfPage": "https://decisioninsights.ai/projects/mpt-mosaic-pretrained-transformer/",
          "name": "MPT (Mosaic Pretrained Transformer)"
        },
        {
          "@id": "https://decisioninsights.ai/projects/stablelm/#project",
          "@type": "SoftwareSourceCode",
          "mainEntityOfPage": "https://decisioninsights.ai/projects/stablelm/",
          "name": "StableLM"
        },
        {
          "@id": "https://decisioninsights.ai/projects/text-generation-inference/#project",
          "@type": "SoftwareSourceCode",
          "mainEntityOfPage": "https://decisioninsights.ai/projects/text-generation-inference/",
          "name": "Text Generation Inference"
        },
        {
          "@id": "https://decisioninsights.ai/projects/llm-guard/#project",
          "@type": "SoftwareSourceCode",
          "mainEntityOfPage": "https://decisioninsights.ai/projects/llm-guard/",
          "name": "LLM Guard"
        }
      ]
    },
    {
      "@type": "PropertyValue",
      "name": "Related organizations",
      "propertyID": "https://decisioninsights.ai/ns#relatedOrganizations",
      "value": [
        {
          "@id": "https://decisioninsights.ai/registry/mistral-ai/#organization",
          "@type": "Organization",
          "mainEntityOfPage": "https://decisioninsights.ai/registry/mistral-ai/",
          "name": "Mistral AI"
        },
        {
          "@id": "https://decisioninsights.ai/registry/d-matrix/#organization",
          "@type": "Organization",
          "mainEntityOfPage": "https://decisioninsights.ai/registry/d-matrix/",
          "name": "d-Matrix"
        },
        {
          "@id": "https://decisioninsights.ai/registry/baseten/#organization",
          "@type": "Organization",
          "mainEntityOfPage": "https://decisioninsights.ai/registry/baseten/",
          "name": "Baseten"
        },
        {
          "@id": "https://decisioninsights.ai/registry/vllm-blog/#organization",
          "@type": "Organization",
          "mainEntityOfPage": "https://decisioninsights.ai/registry/vllm-blog/",
          "name": "vLLM Blog"
        },
        {
          "@id": "https://decisioninsights.ai/registry/cerebras/#organization",
          "@type": "Organization",
          "mainEntityOfPage": "https://decisioninsights.ai/registry/cerebras/",
          "name": "Cerebras"
        },
        {
          "@id": "https://decisioninsights.ai/registry/hugging-face/#organization",
          "@type": "Organization",
          "mainEntityOfPage": "https://decisioninsights.ai/registry/hugging-face/",
          "name": "Hugging Face"
        },
        {
          "@id": "https://decisioninsights.ai/registry/crusoe/#organization",
          "@type": "Organization",
          "mainEntityOfPage": "https://decisioninsights.ai/registry/crusoe/",
          "name": "Crusoe"
        },
        {
          "@id": "https://decisioninsights.ai/registry/ai21-labs/#organization",
          "@type": "Organization",
          "mainEntityOfPage": "https://decisioninsights.ai/registry/ai21-labs/",
          "name": "AI21 Labs"
        }
      ]
    }
  ],
  "author": {
    "@id": "https://decisioninsights.ai/registry/nvidia-corp/#organization",
    "@type": "Organization",
    "mainEntityOfPage": "https://decisioninsights.ai/registry/nvidia-corp/",
    "name": "Nvidia"
  },
  "codeRepository": "https://github.com/nvidia/tensorrt-llm",
  "dateModified": "2026-08-27T03:10:34Z",
  "description": "TensorRT-LLM is an Nvidia software stack for optimized large language model inference on Nvidia GPUs in production environments.",
  "keywords": [
    "Open Source",
    "CUDA",
    "Enterprise",
    "Graphics Processing Unit",
    "Inference",
    "Inference Optimization",
    "Language Models",
    "Latency",
    "Machine Learning",
    "Representational State Transfer",
    "Retrieval Augmented Generation",
    "Services",
    "Software",
    "Throughput",
    "Transformer"
  ],
  "knowsAbout": [
    {
      "@id": "https://decisioninsights.ai/term/ai-infrastructure/#definedterm",
      "@type": "DefinedTerm",
      "mainEntityOfPage": "https://decisioninsights.ai/term/ai-infrastructure/",
      "name": "AI infrastructure"
    },
    {
      "@id": "https://decisioninsights.ai/term/ai-artificial-intelligence/#definedterm",
      "@type": "DefinedTerm",
      "mainEntityOfPage": "https://decisioninsights.ai/term/ai-artificial-intelligence/",
      "name": "Artificial Intelligence"
    },
    {
      "@id": "https://decisioninsights.ai/term/data-center/#definedterm",
      "@type": "DefinedTerm",
      "mainEntityOfPage": "https://decisioninsights.ai/term/data-center/",
      "name": "Data Center"
    },
    {
      "@id": "https://decisioninsights.ai/term/network-operator/#definedterm",
      "@type": "DefinedTerm",
      "mainEntityOfPage": "https://decisioninsights.ai/term/network-operator/",
      "name": "Network Operator"
    },
    {
      "@id": "https://decisioninsights.ai/term/cuda/#definedterm",
      "@type": "DefinedTerm",
      "mainEntityOfPage": "https://decisioninsights.ai/term/cuda/",
      "name": "CUDA"
    },
    {
      "@id": "https://decisioninsights.ai/term/enterprise/#definedterm",
      "@type": "DefinedTerm",
      "mainEntityOfPage": "https://decisioninsights.ai/term/enterprise/",
      "name": "Enterprise"
    },
    {
      "@id": "https://decisioninsights.ai/term/gpu/#definedterm",
      "@type": "DefinedTerm",
      "mainEntityOfPage": "https://decisioninsights.ai/term/gpu/",
      "name": "Graphics Processing Unit"
    },
    {
      "@id": "https://decisioninsights.ai/term/inference/#definedterm",
      "@type": "DefinedTerm",
      "mainEntityOfPage": "https://decisioninsights.ai/term/inference/",
      "name": "Inference"
    },
    {
      "@id": "https://decisioninsights.ai/term/inference-optimization/#definedterm",
      "@type": "DefinedTerm",
      "mainEntityOfPage": "https://decisioninsights.ai/term/inference-optimization/",
      "name": "Inference Optimization"
    },
    {
      "@id": "https://decisioninsights.ai/term/language-models/#definedterm",
      "@type": "DefinedTerm",
      "mainEntityOfPage": "https://decisioninsights.ai/term/language-models/",
      "name": "Language Models"
    },
    {
      "@id": "https://decisioninsights.ai/term/latency/#definedterm",
      "@type": "DefinedTerm",
      "mainEntityOfPage": "https://decisioninsights.ai/term/latency/",
      "name": "Latency"
    },
    {
      "@id": "https://decisioninsights.ai/term/machine-learning-ml/#definedterm",
      "@type": "DefinedTerm",
      "mainEntityOfPage": "https://decisioninsights.ai/term/machine-learning-ml/",
      "name": "Machine Learning"
    },
    {
      "@id": "https://decisioninsights.ai/term/representational-state-transfer-rest/#definedterm",
      "@type": "DefinedTerm",
      "mainEntityOfPage": "https://decisioninsights.ai/term/representational-state-transfer-rest/",
      "name": "Representational State Transfer"
    },
    {
      "@id": "https://decisioninsights.ai/term/retrieval-augmented-generation-rag/#definedterm",
      "@type": "DefinedTerm",
      "mainEntityOfPage": "https://decisioninsights.ai/term/retrieval-augmented-generation-rag/",
      "name": "Retrieval Augmented Generation"
    },
    {
      "@id": "https://decisioninsights.ai/term/services/#definedterm",
      "@type": "DefinedTerm",
      "mainEntityOfPage": "https://decisioninsights.ai/term/services/",
      "name": "Services"
    },
    {
      "@id": "https://decisioninsights.ai/term/software/#definedterm",
      "@type": "DefinedTerm",
      "mainEntityOfPage": "https://decisioninsights.ai/term/software/",
      "name": "Software"
    },
    {
      "@id": "https://decisioninsights.ai/term/throughput/#definedterm",
      "@type": "DefinedTerm",
      "mainEntityOfPage": "https://decisioninsights.ai/term/throughput/",
      "name": "Throughput"
    },
    {
      "@id": "https://decisioninsights.ai/term/transformer/#definedterm",
      "@type": "DefinedTerm",
      "mainEntityOfPage": "https://decisioninsights.ai/term/transformer/",
      "name": "Transformer"
    }
  ],
  "mainEntityOfPage": "https://decisioninsights.ai/projects/tensorrt-llm/",
  "maintainer": {
    "@id": "https://decisioninsights.ai/registry/nvidia-corp/#organization",
    "@type": "Organization",
    "mainEntityOfPage": "https://decisioninsights.ai/registry/nvidia-corp/",
    "name": "Nvidia"
  },
  "name": "TensorRT-LLM",
  "publisher": {
    "@id": "https://decisioninsights.ai/registry/nvidia-corp/#organization",
    "@type": "Organization",
    "mainEntityOfPage": "https://decisioninsights.ai/registry/nvidia-corp/",
    "name": "Nvidia"
  },
  "subjectOf": [
    {
      "@id": "https://decisioninsights.ai/nvidia-launches-dynamo-1.0-open-source-software-for-ai-inference-at-scale/#blogposting",
      "@type": "NewsArticle",
      "headline": "NVIDIA launches Dynamo 1.0 open source software for AI inference at scale",
      "isBasedOn": {
        "@type": "CreativeWork",
        "sourceOrganization": {
          "@type": "Organization",
          "name": "GlobeNewswire"
        },
        "url": "https://www.globenewswire.com/news-release/2026/03/16/3256759/0/en/NVIDIA-Enters-Production-With-Dynamo-the-Broadly-Adopted-Inference-Operating-System-for-AI-Factories.html"
      },
      "url": "https://decisioninsights.ai/nvidia-launches-dynamo-1.0-open-source-software-for-ai-inference-at-scale/"
    }
  ],
  "url": "https://github.com/nvidia/tensorrt-llm"
}
What we add

Graph

A protocol or open source project has no press office, and often no site of its own to publish from at all. Nothing shows the coverage written about it elsewhere. We track and link every article that does.

NewsArticle NVIDIA launches Dynamo 1.0 open source software for AI inference at scale

Topic graph

A wire service tags a release with a category, once. It doesn't maintain a durable graph over time. We connect them to a topic graph an agent can query.

AI infrastructure https://decisioninsights.ai/term/ai-infrastructure/ Artificial Intelligence https://decisioninsights.ai/term/ai-artificial-intelligence/ Data Center https://decisioninsights.ai/term/data-center/ and 15 more

Counted facts

A protocol or open source project keeps no vendor list and publishes no figures of its own to check this against. This counts how it actually shows up across the graph -- articles that name it, the organizations named alongside it in those articles, similar projects, and organizations whose topic tags overlap with its own -- computed, not curated.

Articles mentioning this entity 1 Organizations named alongside this entity 9 Related projects TensorRT, vLLM, Megatron-LM, OpenLLM, MPT (Mosaic Pretrained Transformer), StableLM, Text Generation Inference, LLM Guard Related organizations Mistral AI, d-Matrix, Baseten, vLLM Blog, Cerebras, Hugging Face, Crusoe, AI21 Labs

The person who sent this agent gets an answer they can act on

Somebody dispatched this agent to evaluate TensorRT-LLM for a real decision: a shortlist, a vendor comparison, a purchase. "TensorRT-LLM makes X" isn't something they can act on; they need to know the claim is real and where it came from. Follow one enriched link from Act 2 and see what the agent can actually hand back to them:

  1. The record SoftwareSourceCode TensorRT-LLM https://decisioninsights.ai/projects/tensorrt-llm/
  2. One of its 1 linked records NewsArticle NVIDIA launches Dynamo 1.0 open source software for AI inference at scale https://decisioninsights.ai/nvidia-launches-dynamo-1.0-open-source-software-for-ai-inference-at-scale/
  3. The primary source CreativeWork globenewswire.com https://www.globenewswire.com/news-release/2026/03/16/3256759/0/en/NVIDIA-Enters-Production-With-Dynamo-the-Broadly-Adopted-Inference-Operating-System-for-AI-Factories.html

Our summary is written by Decision Insights Record. The source keeps its own byline. Both are in the JSON.