Introducing Prime Inference: We've served trillions of tokens for RL and dedicated customer deployments To own your intelligence, you need to own your inference Unpacking our inference stack

Congrats @CoreWeave on RL Rollouts! RL post-training involves a lot of back and forth: train the model, generate responses, then train again. Inference workers need to load the updated model weights each time. As models get bigger, that can leave GPUs waiting. CoreWeave’s new service uses ModelExpress and Router in NVIDIA Dynamo to speed up those reloads with minimal downtime. Working with us and @youdotcom, CoreWeave achieved 15× faster model reloads compared with its baseline while post-training Nemotron 3.5 Lightning. Check out their blog below for details

We’re looking for our next cohort of graduate fellows. Our 2027–2028 Graduate Fellowship Program is open to Ph.D. students worldwide with awards up to $60,000, plus mentorship and technical support. Apply by October 30: nvda.ws/4rGKDhv

My agent tells me that inference engineering job openings have doubled in the past 6 months. I think that's an underestimate. Demand for inference has inflected, again. So too has demand for engineers who can operate AI models in production.

Multimodal models put different demands on vision encoding, prefill and decoding. Separating vision encoding from the other stages can reduce resource contention and help models respond faster, but only for the right workloads. See how EPD disaggregation works, when it helps and what to consider before using it: nvda.ws/4xUFUv2

Our RL stack now supports NIXL weight transfer, reducing trainer-to-inference transfer time 9x compared with NCCL: from 86 seconds down to single-digit seconds for an 800B-parameter model, and even <4 seconds in our experiments. For prime-rl users, this means over 25% more throughput end-to-end compared with our previous speed. It also clears the way for fault-tolerant, elastic inference scaling that NCCL's rigid process groups made difficult.