Torsten Hoefler

The Geometry of LLM Quantization: GPTQ as Babai's Nearest Plane Algorithm

Bridging the Gap Between Promise and Performance for Microscaling FP4 Quantization

Beyond Outliers: A Study of Optimizers Under Quantization

Multi-Head RAG: Solving Multi-Aspect Problems with LLMs

Affordable AI Assistants with Knowledge Graph of Thoughts

Which LLM to pick? Online Active Model Selection for Large Language Models

EntryPrune: Neural Network Feature Selection using First Impressions

Epidemiology of Large Language Models: A Benchmark for Observational Distribution Knowledge

Active Model Selection for Large Language Models

Addition Circuit: How LLMs Add in Their Heads using State Vectors

HALO: Hadamard-Assisted Lower-Precision Optimization for LLMs

Multi-Head RAG: Solving Multi-Aspect Problems with LLMs

CheckEmbed: Effective Verification of LLM Solutions to Open-Ended Tasks