Learn how @cursor_ai partnered with Together AI, the AI Native Cloud, to deliver real-time inference for AI-powered coding. Cursor's in-editor agents generate code while developers actively edit — requiring responses inside the editor's feedback loop. Together AI built the infrastructure to meet those strict latency targets at scale.

Together AI engineered the full stack on NVIDIA Blackwell: 👉 Production reliability on NVIDIA Blackwell GB200/B200 GPUs under sustained load 👉 Custom kernels for NVIDIA Blackwell tensor cores 👉 Fast weights-to-production cycle with FP4 quantization 👉 Efficient parallelism across NVL72's 72-GPU mesh