Together AI, Equinix and NVIDIA launch Inference Exchange for distributed open-model inference
togethercompute · x · 2026-09-03
Together AI partnered with Equinix and NVIDIA on Equinix Inference Exchange, combining NVIDIA Enterprise Reference Architectures, Together AI's inference platform (200+ open-source models), and Equinix's global data centers to run enterprise inference closer to data and users with lower latency and cost. Equinix also launched Fabric One for connecting distributed AI environments, framing open source as the default enterprise AI path.
More from Infra
- Perplexity adds hybrid compute to Mac app: local models for sensitive data — AravSrinivas · 2026-09-03
- Run Claude Code on Google Cloud in 60 seconds with gcloud auth and 3 env vars — fhinkel · 2026-09-03
- Compute and connectivity will bottleneck for 20 years: AWS and Starlink TAMs are OOMs bigger — curious_vii · 2026-09-03
- Nvidia reportedly in talks to buy Hugging Face for over $13 billion — KoseteBamse · 2026-09-03
- Researchers rented 51,500 GPUs across AWS, Azure and GCP for a two-hour cloudburst experiment — mcraddock · 2026-09-03
- Analyst: Fabrinet well positioned for CPO, but TSMC Coupe maturity could shift dynamics — BenBajarin · 2026-09-03