Early-Signal Detector

method · first seen 5 Oct 2026

large language model quantization

Applying low-bit weight and activation compression to large language models to reduce memory and compute cost.

Mentions per week

0119 May11 Aug10 NovPapersCodeDiscussion

PapersCodeDiscussion

Earliest sources

Latest sources

Mentioned together with

post-training quantizationvector quantizationstraight-through estimatorGPTQ