From the source
Baseten has joined the
NVIDIA Nemotron Coalition, expanding its collaboration with NVIDIA to advance open frontier models and accelerate enterprise AI adoption.
- The company says it will contribute insights from enterprise workloads and expertise in post-training and inference to help advance NVIDIA Nemotron, NVIDIA's family of open models, and the broader open-source ecosystem.
- Baseten says it was a day-zero launch partner for Nemotron Super 3.5 VL and Nemotron 3 Ultra, and that it supports customers such as
Harvey and CodeRabbit with early model access, customization and deployment.
- For CodeRabbit, it customized Nemotron 3.5 Lightning for code review routing using NVIDIA NeMo tools for supervised fine-tuning and RL on Baseten Training.
- In a fixed evaluation of 1,000 tasks, agreement with CodeRabbit's routing policy rose from 75.8% to 80.7%, and CodeRabbit also achieved 50.4% lower inference cost at saturated throughput.
- Baseten says a single NVIDIA Hopper GPU sustained up to 100 concurrent real-time audio streams over WebSocket in its published benchmark for Nemotron 3.5 ASR Streaming.
- Baseten Loops, which connects managed RL workflows with deployment to Dedicated Inference, supports Nemotron 3.5 Super VL and Nemotron 3 Ultra, with Nemotron 3.5 Super VL available with both BF16 and NVFP4 training.





