{
  "version": "https://jsonfeed.org/version/1.1",
  "title": "AI News: Together AI",
  "home_page_url": "https://ai-news.ypetit.net/sources/together-ai/",
  "feed_url": "https://ai-news.ypetit.net/feed/source/together-ai.json",
  "description": "Latest publications from Together AI, aggregated by AI News from the official source.",
  "language": "en",
  "items": [
    {
      "id": "https://www.together.ai/blog/together-compiler-continual-compilation-for-ai-inference",
      "url": "https://www.together.ai/blog/together-compiler-continual-compilation-for-ai-inference",
      "title": "Together AI: Together Compiler: Continual Compilation for AI inference",
      "summary": "Together Compiler uses agents and persistent engines to optimize open models in under 24 hours, delivering up to 3.7x higher throughput as traffic changes.",
      "date_published": "2026-11-04T00:00:00.000Z",
      "tags": [
        "blog",
        "Together AI"
      ],
      "authors": [
        {
          "name": "Together AI"
        }
      ]
    },
    {
      "id": "https://www.together.ai/blog/polymorphic-inference",
      "url": "https://www.together.ai/blog/polymorphic-inference",
      "title": "Together AI: Polymorphic Inference: self-tuning inference for open models",
      "summary": "Models, traffic and chips are constantly changing. Polymorphic Inference adapts to each, and Together Compiler uses AI agents to keep production inference tuned.",
      "date_published": "2026-11-04T00:00:00.000Z",
      "tags": [
        "blog",
        "Together AI"
      ],
      "authors": [
        {
          "name": "Together AI"
        }
      ]
    },
    {
      "id": "https://www.together.ai/blog/auto-repair-for-together-gpu-clusters",
      "url": "https://www.together.ai/blog/auto-repair-for-together-gpu-clusters",
      "title": "Together AI: Auto repair for Together GPU Clusters: from GPU fault to healthy node",
      "summary": "Together GPU Clusters auto repair detects GPU, host and fabric faults, picks the lightest fix, and lets you decide per fault and per Xid code which repairs run automatically. Here is how it works.",
      "date_published": "2026-10-27T00:00:00.000Z",
      "tags": [
        "blog",
        "Together AI"
      ],
      "authors": [
        {
          "name": "Together AI"
        }
      ]
    },
    {
      "id": "https://www.together.ai/blog/together-post-training",
      "url": "https://www.together.ai/blog/together-post-training",
      "title": "Together AI: Together Post-Training: frontier-grade model shaping, the way that fits you",
      "summary": "Post-train open LLMs like Qwen, GLM and Kimi into custom models you own, with SFT or RL. You write the training loop. Together runs the hard infrastructure.",
      "date_published": "2026-10-19T00:00:00.000Z",
      "tags": [
        "blog",
        "Together AI"
      ],
      "authors": [
        {
          "name": "Together AI"
        }
      ]
    },
    {
      "id": "https://www.together.ai/blog/meta-muse-spark-open",
      "url": "https://www.together.ai/blog/meta-muse-spark-open",
      "title": "Together AI: Meta Muse Spark Open is live on Together AI",
      "summary": "Meta Muse Spark Open, Meta's open-weight model for agentic coding, is live on Together AI with a 1M-token context window on serverless and dedicated infrastructure.",
      "date_published": "2026-10-15T00:00:00.000Z",
      "tags": [
        "blog",
        "Together AI"
      ],
      "authors": [
        {
          "name": "Together AI"
        }
      ]
    },
    {
      "id": "https://www.together.ai/blog/expanding-our-enterprise-inference-capacity-with-ibm-cloud-and-nvidia",
      "url": "https://www.together.ai/blog/expanding-our-enterprise-inference-capacity-with-ibm-cloud-and-nvidia",
      "title": "Together AI: Expanding our enterprise inference capacity with IBM Cloud and NVIDIA",
      "summary": "Enterprises can now run open models at production scale on a dedicated B300 inference cluster, built by Together AI, IBM Cloud, and NVIDIA",
      "date_published": "2026-10-06T00:00:00.000Z",
      "tags": [
        "blog",
        "Together AI"
      ],
      "authors": [
        {
          "name": "Together AI"
        }
      ]
    },
    {
      "id": "https://www.together.ai/blog/together-link-frontier-quality-open-models-in-the-harness-you-already-use",
      "url": "https://www.together.ai/blog/together-link-frontier-quality-open-models-in-the-harness-you-already-use",
      "title": "Together AI: Together Link: open models in the harness you already use. Start with one command today.",
      "summary": "Together Link brings frontier open models like GLM 5.3 and Kimi K3 into the coding agent your team already uses, cutting model spend by over 50%.",
      "date_published": "2026-10-05T00:00:00.000Z",
      "tags": [
        "blog",
        "Together AI"
      ],
      "authors": [
        {
          "name": "Together AI"
        }
      ]
    },
    {
      "id": "https://www.together.ai/blog/how-to-train-your-own-jev",
      "url": "https://www.together.ai/blog/how-to-train-your-own-jev",
      "title": "Together AI: How to train your own Jev for $17",
      "summary": "We just launched our own Jev-like classifier, together/Tev1-4B-experimental, on top of Qwen3.5 4B on Together’s serverless platform. In this blog post we’ll show you how to fine-tune your own version!",
      "date_published": "2026-09-23T00:00:00.000Z",
      "tags": [
        "blog",
        "Together AI"
      ],
      "authors": [
        {
          "name": "Together AI"
        }
      ]
    },
    {
      "id": "https://www.together.ai/blog/canary-rollouts-upgrade-models-in-production-without-downtime",
      "url": "https://www.together.ai/blog/canary-rollouts-upgrade-models-in-production-without-downtime",
      "title": "Together AI: Canary rollouts: upgrade models in production without downtime",
      "summary": "A hard model swap exposes every user at once, and rolling back means cold-starting the old deployment under pressure. Here's how staged traffic ramps, metric gates, and automatic rollback work on dedicated inference.",
      "date_published": "2026-09-22T00:00:00.000Z",
      "tags": [
        "blog",
        "Together AI"
      ],
      "authors": [
        {
          "name": "Together AI"
        }
      ]
    },
    {
      "id": "https://www.together.ai/blog/global-fintech-scales-coding-agent-traffic-with-dedicated-model-inference",
      "url": "https://www.together.ai/blog/global-fintech-scales-coding-agent-traffic-with-dedicated-model-inference",
      "title": "Together AI: How a global fintech scaled coding agent traffic with Dedicated Model Inference",
      "summary": "Inside a global bank's shift to self-serve dedicated inference: how Together's DMI gave engineering teams direct control over scaling, models, and testing.",
      "date_published": "2026-09-18T00:00:00.000Z",
      "tags": [
        "blog",
        "Together AI"
      ],
      "authors": [
        {
          "name": "Together AI"
        }
      ]
    },
    {
      "id": "https://www.together.ai/blog/migrating-from-closed-to-open-source-models",
      "url": "https://www.together.ai/blog/migrating-from-closed-to-open-source-models",
      "title": "Together AI: Migrating from closed to open source models, Together",
      "summary": "Moving from closed to open source models can take weeks, not years. A five-stage playbook: discover, evaluate, adapt, decide, and production.",
      "date_published": "2026-09-16T00:00:00.000Z",
      "tags": [
        "blog",
        "Together AI"
      ],
      "authors": [
        {
          "name": "Together AI"
        }
      ]
    }
  ]
}