Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Nemotron 3 Super: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Model for Agentic Reasoning
NVIDIA, :, Aakshita Chandiramani +544
We describe the pre-training, post-training, and quantization of Nemotron 3 Super, a 120 billion (active 12 billion) parameter hybrid Mamba-Attention Mixture-of-Experts model. Nemo…
cs.LG2026
Extending Puzzle for Mixture-of-Experts Reasoning Models with Application to GPT-OSS Acceleration
Akhiad Bercovich, Nir Ailon, Vladimir Anisimov +21
Reasoning-focused LLMs improve answer quality by generating longer reasoning traces, but the additional tokens dramatically increase serving cost, motivating inference optimization…