LLM quantization

LiquidGEMM

LiquidGEMM: Hardware-Efficient W4A8 GEMM Kernel for High-Performance LLM Serving

Trackedfirst seen Sep 1, 2025

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Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.