7 citations · 9 across the 20 of their papers we have counts for
8 papers · 1 filter
Heterogeneous Parallelism for Multimodal Large Language Model Training
Yashaswi Karnati, Kamran Jafari, Akash Mehra +10
Foundation model training is becoming multimodal, from post-training pipelines to large-scale pretraining. As modality coverage broadens, context windows grow, and encoder LLM scal…
X-Token: Projection-Guided Cross-Tokenizer Knowledge Distillation
Sharath Turuvekere Sreenivas, Adithyakrishna Venkatesh Hanasoge, Mingyu Yang +4
Cross-tokenizer knowledge distillation allows a student model to learn from teachers with incompatible vocabularies. Prior work operates on hidden states or logits; the latter is p…
Star Elastic: Many-in-One Reasoning LLMs with Efficient Budget Control
Ali Taghibakhshi, Ruisi Cai, Saurav Muralidharan +17
Training a family of large language models (LLMs), either from scratch or via iterative compression, is prohibitively expensive and inefficient, requiring separate training runs fo…
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…
MoE Parallel Folding: Heterogeneous Parallelism Mappings for Efficient Large-Scale MoE Model Training with Megatron Core
Dennis Liu, Zijie Yan, Xin Yao +15
Mixture of Experts (MoE) models enhance neural network scalability by dynamically selecting relevant experts per input token, enabling larger model sizes while maintaining manageab…