6 papers
SPEED-Bench: A Unified and Diverse Benchmark for Speculative Decoding
Talor Abramovich, Maor Ashkenazi, Izzy Putterman +5
Speculative Decoding (SD) has emerged as a critical technique for accelerating Large Language Model (LLM) inference. Unlike deterministic system optimizations, SD performance is in…
Accelerating RL Post-Training Rollouts via System-Integrated Speculative Decoding
Hayate Iso, Tiyasa Mitra, Sudipta Mondal +15
RL post-training of frontier language models is increasingly bottlenecked by autoregressive rollout generation, making rollout acceleration a central systems challenge. Many existi…
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…
LatentMoE: Toward Optimal Accuracy per FLOP and Parameter in Mixture of Experts
Venmugil Elango, Nidhi Bhatia, Roger Waleffe +13
Mixture of Experts (MoEs) have become a central component of many state-of-the-art open-source and proprietary large language models. Despite their widespread adoption, it remains…
Helix Parallelism: Rethinking Sharding Strategies for Interactive Multi-Million-Token LLM Decoding
Nidhi Bhatia, Ankit More, Ritika Borkar +7
As LLMs scale to multi-million-token KV histories, real-time autoregressive decoding under tight Token-to-Token Latency (TTL) constraints faces growing pressure. Two core bottlenec…
Beyond the Buzz: A Pragmatic Take on Inference Disaggregation
Tiyasa Mitra, Ritika Borkar, Nidhi Bhatia +10
As inference scales to multi-node deployments, disaggregation - splitting inference into distinct phases - offers a promising path to improving the throughput-interactivity Pareto…