QTEA: Ternary LLMs with Sparse Residual Salient Weight and By-Column Optimization
This story is from 2026-09-02. It is preserved in the archive; the latest stories are on the live feed.
arXiv:2609.00224v2 Announce Type: new Abstract: Weight-only post-training quantization (PTQ) can alleviate the computational burden of serving large language models (LLMs) at scale. However, existing PTQ methods often fail to generalize across models and suffer severe accuracy loss below 2 bits. Ma…
Read the full story at arXiv cs.LG ↗
Timeline · 1 report
- 2026-09-02 04:00 · arXiv cs.LG
QTEA: Ternary LLMs with Sparse Residual Salient Weight and By-Column Optimization