LLM quantization

MGRQ

MGRQ: Post-Training Quantization For Vision Transformer With Mixed Granularity Reconstruction

Trackedfirst seen Jun 13, 2024

Present, but with little supersession signal in the knowledge base

0 papers critique it · 0 beat it on benchmarks

What to use instead

Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.