Today we're introducing Verda Inference, in preview, with day-0 access to Kimi K3.1 Pro, in partnership with @Kimi_Moonshot 🧵
Frontier open-weight models through one API, engineered for every request, from a single prompt to long-horizon agents.
Day one at @raydistributed and @vllm_project Summit ⚡ and we're on the schedule today
3 PM, Lightning Theater: Helen Zhao (@RedHat_AI) on scaling drafter training in real time across a full Verda GB300 rack with vLLM, Mooncake & Speculators.
Booth's open all day on the expo floor. Come around, grab some Finnish chocolate 🍫 and talk shop: GPUs, distributed training, scaling AI in production.
Big news 🚀 We are partnering with @Supermicro to scale our full-stack AI infrastructure.
This partnership expands our capacity of NVIDIA Blackwell systems for frontier labs, AI-native teams, and enterprise customers worldwide.
Read the press release: