GSQ-RCO: Better Non-Uniform GGUF Quantization
Exploring GSQ and RCO, two advanced methods for accurate low-bit LLM quantization, this presentation delves into Gumbel-Softmax sampling and Riemannian optimization for precision allocation.
Faculty & Researcher Profile
Michael Helcig
Student at ETH, PhD candidate at ISTA DASLab
Michael Helcig is a PhD candidate at ISTA DASLab and a student at ETH Zürich, focusing on advanced neural network applications and low-power high-performance VLSI design.
1standalone talk1total lecture1hrecorded
Intellectual Web & Academic Lineage · Michael Helcig
1 connectionVerified alma mater degrees, faculty appointments, co-authors, doctoral lineage, and intellectual peers across the archive.
Faculty Appointmentinstitution
ETH Zürich
4 courses · 57 lectures
Student at ETH, PhD candidate at ISTA DASLab
Standalone talks by Michael Helcig
1Self-contained public lectures, keynote addresses, and research seminars.