Seonjin Na

Industry-standard GPU memory sanitizers harbor major blind spots across core memory spaces, finally quantifiable through 149 targeted CUDA stress tests.

Achieving six times the inference throughput of current LLMs while maintaining accuracy, Nemotron 3 Ultra redefines performance benchmarks for agentic reasoning tasks.

Speculative decoding, typically used post-RL, can be integrated directly into RL training loops to accelerate LLM rollout generation by up to 2.5x.

Nemotron 3 Super proves you can achieve comparable accuracy to existing 120B models, but with significantly higher inference throughput, by combining Mamba, Attention, and Mixture-of-Experts.