NVIDIA releases Nemotron 3.5 Lightning, a lightweight model designed specifically for AI agents with only 3B active parameters out of 30B total, balancing efficiency and capability, with immediate production support from vLLM.
A comprehensive benchmark by the vLLM team reveals that TurboQuant generally underperforms FP8 quantization and is only potentially viable for extreme memory-constrained edge deployments.
AWS details the infrastructure supporting the full foundation model lifecycle from pre-training and post-training to inference, revealing a paradigm shift from a single scaling law to three, and the deep integration trend of open-source software stacks with cloud infrastructure.
NVIDIA releases Nemotron 3 Nano Omni, a 30B-parameter MoE model that achieves extreme efficiency by activating only 3B parameters, offering a unified and cost-effective solution for multimodal AI agents.