{
  "kind": "tag",
  "slug": "ai-infrastructure-topic",
  "id": 17791452103823983,
  "name": "AI Infrastructure",
  "type": "topic",
  "aliases": [
    "AI compute infrastructure",
    "ai_infrastructure",
    "AI infrastructure",
    "model-serving infrastructure"
  ],
  "diffbot_id": null,
  "story_count_14d": 871,
  "cooccurring_tags": [
    {
      "id": 17723038993834764,
      "slug": "artificial-intelligence-topic",
      "name": "Artificial Intelligence",
      "type": "topic",
      "count": 416
    },
    {
      "id": 17791452102628180,
      "slug": "inference-optimization-topic",
      "name": "Inference Optimization",
      "type": "topic",
      "count": 175
    },
    {
      "id": 17723038994323052,
      "slug": "arxiv-organization",
      "name": "arXiv",
      "type": "organization",
      "count": 169
    },
    {
      "id": 17791452097663640,
      "slug": "ai-agents-topic",
      "name": "AI Agents",
      "type": "topic",
      "count": 126
    },
    {
      "id": 17723038993835295,
      "slug": "cloud-computing-topic",
      "name": "Cloud Computing",
      "type": "topic",
      "count": 110
    },
    {
      "id": 17791452099123760,
      "slug": "llm-evals-topic",
      "name": "LLM Evals",
      "type": "topic",
      "count": 90
    },
    {
      "id": 17723038993599257,
      "slug": "openai-organization",
      "name": "OpenAI",
      "type": "organization",
      "count": 62
    },
    {
      "id": 17782518580601405,
      "slug": "machine-learning-research-topic",
      "name": "Machine Learning Research",
      "type": "topic",
      "count": 60
    },
    {
      "id": 17791452103543441,
      "slug": "gpu-clusters-topic",
      "name": "GPU Clusters",
      "type": "topic",
      "count": 60
    },
    {
      "id": 17723038993599085,
      "slug": "nvidia-organization",
      "name": "Nvidia",
      "type": "organization",
      "count": 58
    },
    {
      "id": 17730948119041167,
      "slug": "multimodal-ai-topic",
      "name": "Multimodal AI",
      "type": "topic",
      "count": 52
    },
    {
      "id": 17723038993598995,
      "slug": "aws-organization",
      "name": "AWS",
      "type": "organization",
      "count": 52
    },
    {
      "id": 17731007202817379,
      "slug": "zhipu-ai-organization",
      "name": "Zhipu AI",
      "type": "organization",
      "count": 50
    },
    {
      "id": 17723038993835921,
      "slug": "cybersecurity-topic",
      "name": "Cybersecurity",
      "type": "topic",
      "count": 48
    },
    {
      "id": 17723038993840726,
      "slug": "venture-capital-markets-topic",
      "name": "Venture Capital Markets",
      "type": "topic",
      "count": 48
    }
  ],
  "top_sources": [
    {
      "name": "arxiv-ai-infra-inference-ops",
      "slug": "arxiv-ai-infra-inference-ops",
      "count": 73
    },
    {
      "name": "zhipu-ai-release-notes",
      "slug": "zhipu-ai-release-notes",
      "count": 52
    },
    {
      "name": "baseten-blog",
      "slug": "baseten-blog",
      "count": 48
    },
    {
      "name": "arxiv-ai-agents-tool-use",
      "slug": "arxiv-ai-agents-tool-use",
      "count": 38
    },
    {
      "name": "arxiv-frontier-methods-select",
      "slug": "arxiv-frontier-methods-select",
      "count": 30
    },
    {
      "name": "aws-machine-learning-blog",
      "slug": "aws-machine-learning-blog",
      "count": 20
    },
    {
      "name": "huggingface-nlp-blog",
      "slug": "huggingface-nlp-blog",
      "count": 18
    },
    {
      "name": "arxiv-rag-search-knowledge",
      "slug": "arxiv-rag-search-knowledge",
      "count": 12
    },
    {
      "name": "databricks-ai-research",
      "slug": "databricks-ai-research",
      "count": 10
    },
    {
      "name": "nvidia-blog",
      "slug": "nvidia-blog",
      "count": 10
    }
  ],
  "recent_stories": [
    {
      "id": 1780315090368785219,
      "slug": "uniscale-adaptive-unified-inference-scaling-via-online-joint-8785219",
      "headline": "UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling",
      "source": "arxiv-rag-search-knowledge",
      "home_domain": "engineering-technology",
      "published_date": "2026-06-01"
    },
    {
      "id": 1780315090102845559,
      "slug": "uniscale-adaptive-unified-inference-scaling-via-online-joint-2845559",
      "headline": "UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling",
      "source": "arxiv-rag-search-knowledge",
      "home_domain": "engineering-technology",
      "published_date": "2026-06-01"
    },
    {
      "id": 1780313867606096182,
      "slug": "specdb-llm-generated-customized-databases-via-feature-orient-6096182",
      "headline": "SpecDB: LLM-Generated Customized Databases via Feature-Oriented Decomposition",
      "source": "arxiv-rag-search-knowledge",
      "home_domain": "engineering-technology",
      "published_date": "2026-06-01"
    },
    {
      "id": 1780313867853240622,
      "slug": "specdb-llm-generated-customized-databases-via-feature-orient-3240622",
      "headline": "SpecDB: LLM-Generated Customized Databases via Feature-Oriented Decomposition",
      "source": "arxiv-rag-search-knowledge",
      "home_domain": "engineering-technology",
      "published_date": "2026-06-01"
    },
    {
      "id": 1780313782506254388,
      "slug": "speculative-pipeline-decoding-higher-accruacy-and-zero-bubbl-6254388",
      "headline": "Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline Parallelism",
      "source": "arxiv-rag-search-knowledge",
      "home_domain": "engineering-technology",
      "published_date": "2026-06-01"
    },
    {
      "id": 1780313782769091003,
      "slug": "speculative-pipeline-decoding-higher-accruacy-and-zero-bubbl-9091003",
      "headline": "Speculative Pipeline Decoding: Higher-Accruacy and Zero-Bubble Speculation via Pipeline Parallelism",
      "source": "arxiv-rag-search-knowledge",
      "home_domain": "engineering-technology",
      "published_date": "2026-06-01"
    },
    {
      "id": 1780313718335732181,
      "slug": "aim-a-practical-approach-to-automated-index-management-for-s-5732181",
      "headline": "AIM: A practical approach to automated index management for SQL databases",
      "source": "arxiv-rag-search-knowledge",
      "home_domain": "engineering-technology",
      "published_date": "2026-06-01"
    },
    {
      "id": 1780313718571542356,
      "slug": "aim-a-practical-approach-to-automated-index-management-for-s-1542356",
      "headline": "AIM: A practical approach to automated index management for SQL databases",
      "source": "arxiv-rag-search-knowledge",
      "home_domain": "engineering-technology",
      "published_date": "2026-06-01"
    },
    {
      "id": 1780313627483804734,
      "slug": "incremental-bpe-tokenization-3804734",
      "headline": "Incremental BPE Tokenization",
      "source": "arxiv-rag-search-knowledge",
      "home_domain": "engineering-technology",
      "published_date": "2026-06-01"
    },
    {
      "id": 1780313627770575427,
      "slug": "incremental-bpe-tokenization-0575427",
      "headline": "Incremental BPE Tokenization",
      "source": "arxiv-rag-search-knowledge",
      "home_domain": "engineering-technology",
      "published_date": "2026-06-01"
    },
    {
      "id": 1780313240647338596,
      "slug": "light-interaction-training-free-inference-acceleration-for-i-7338596",
      "headline": "Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models",
      "source": "arxiv-model-efficiency-engineering",
      "home_domain": "engineering-technology",
      "published_date": "2026-06-01"
    },
    {
      "id": 1780313240874133978,
      "slug": "light-interaction-training-free-inference-acceleration-for-i-4133978",
      "headline": "Light Interaction: Training-Free Inference Acceleration for Interactive Video World Models",
      "source": "arxiv-model-efficiency-engineering",
      "home_domain": "engineering-technology",
      "published_date": "2026-06-01"
    }
  ]
}