LLM quantization
MixLLM: LLM Quantization with Global Mixed-precision between Output-features and Highly-efficient System Design
Cited as a baseline — critiqued by newer work, not yet beaten on a benchmark here
1 papers critique it · 0 beat it on benchmarks
Verbatim critique sentences, each from a paper that cites MixLLM as a baseline.
its reliance on naive thresholding and neglect of activation distortion in weight-activation joint quantization often lead to suboptimal performance
Recent methods in the same sub-problem, not yet superseded in the knowledge base — arXiv benchmark leaders, not vetted production recommendations.