ProductsProduct / feature launchHardware & Compute · Efficiency & Inference · Business, Funding & Industry1 source · Oct 6, 2026

Expanding our enterprise inference capacity with IBM Cloud and NVIDIA

Enterprises can now run open models at production scale on a dedicated B300 inference cluster, built by Together AI, IBM Cloud, and NVIDIA

NVIDIANVIDIA BlackwellIBMTogether AI
Proof1 independent outlet
Read at Together AI Blog ↗← Today

Sources (1)

Extractive summary: sentences quoted from the sources.

Before this

  1. Oct 1, 2026unslothai/unsloth v0.1.902-beta: Command Palette + Desktop UI/UX
  2. Sep 29, 2026NVIDIA/TensorRT-LLM v1.3.0rc29
  3. Sep 22, 2026vllm-project/vllm v0.30.0
  4. Jun 26, 2026sgl-project/sglang v0.5.14
  5. Jun 18, 2026pytorch/pytorch v2.12.1: PyTorch 2.12.1 Release, bug fix release
  6. Jun 13, 2026sgl-project/sglang v0.5.13

Related

Paper
arXiv (AI, ML, NLP, CV, robotics, multi-agent)4d ago

Democratizing MoE inference on commodity GPUs with CoMoE

Paper
SiliconANGLE: AI2d ago

CoreWeave targets AI inference bottlenecks with full-stack optimization

NVIDIA Technical Blog11d ago

Expanding AI Storage Access with NVIDIA cuObject and the NVIDIA SCADA Server SDK

Vendor claim only
AWS Machine Learning Blog3d ago

Share GPU clusters across teams with isolation and fairness using Amazon SageMaker HyperPod