inference/research
verifiedhigh · 0.88updated 2026-10-03

ZeroQuant-V2: Exploring Post-training Quantization in LLMs from Comprehensive Study to Low Rank Compensation (Yao et al.)

paper

Fields

id
sources/qlab-zeroquant-v2-paper
URL
https://arxiv.org/abs/2303.08302
Publisher
arXiv
Kind
paper
Published
2023-03-15
Accessed
2026-10-03
notes
v3. Sensitivity study across 125M-176B plus the Low-Rank Compensation (LoRC) method.

Notes

v3. Sensitivity study across 125M-176B plus the Low-Rank Compensation (LoRC) method.

Cross-references

This record references no other records.