Counting papers with at most 25 authors, so collaboration author lists do not stand in for the people here.
- Bakke Graduate UniversityUS2 papers
- FZU ‒ Institute of Physics of the Academy of Sciences of the Czech RepublicCZ2 papers
- Institut de Mécanique et d'Ingénierie de BordeauxFR2 papers
- Polish Academy of SciencesPL2 papers
- University of WarsawPL2 papers
- Czech Technical University in PragueCZ1 paper
- ETH ZurichCH1 paper
- Institute of Inorganic Chemistry of the Slovak Academy of SciencesSK1 paper
- Open Rights GroupGB1 paper
- University of SeoulKR1 paper
- University of TübingenDE1 paper
- Walmart (United States)US1 paper
3 papers · 1 filter
Unfolding the Leech Lattice: Fused Multi-Shell Decoding and VRAM Layouts for 2-Bit LLM Weights
Pier-Jean Malandrino
Leech-lattice vector quantization holds the strongest reported 2-bit quality under its own evaluation protocol. Its kernel decodes one shell; we found no implementation of the mult…
LEAP: Layer-wise Exit-Aware Pretraining for Efficient Transformer Inference
Shashank Kapadia, Deep Naryan Mishra, Sujal Reddy Alugubelli +4
Layer-aligned distillation and convergence-based early exit represent two predominant computational efficiency paradigms for transformer inference; yet we establish that they exhib…
SAGE: Sign-Adaptive Gradient for Memory-Efficient LLM Optimization
Wooin Lee, Hyun-Tae Kim
The AdamW optimizer, while standard for LLM pretraining, is a critical memory bottleneck, consuming optimizer states equivalent to twice the model's size. Although light-state opti…