GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax Sampling
Paper • 2604.18556 • Published • 9
Fabio
Kryohi
·
AI & ML interests
None yet
Recent Activity
liked a model about 1 month ago
chili-lab/Ouro-hybrid-1.4B liked a model about 1 month ago
biohub/ESMC-6B upvoted a paper about 2 months ago
GSQ: Highly-Accurate Low-Precision Scalar Quantization for LLMs via Gumbel-Softmax SamplingOrganizations
None yet
upvoted a paper about 2 months ago