§ feed · storyline
Cursor partners with Together AI for fast in-editor inference
Together AI partners with Cursor to build a real-time inference stack using NVIDIA Blackwell hardware and FP4/TensorRT quantization to keep in-editor agents fast and low-latency.
Together AI teamed with Cursor to build the real-time inference stack that keeps in-editor agents fast and reliable. They productionized NVIDIA Blackwell (B200/GB200), tuning ARM hosts, kernels, and FP4/TensorRT quantization for low latency and rapid model rollouts.
§ sources1 publication · timeline below