Illustration: the project’s public image, pixelated by RepoMasters. Credits
BetaRare

intel/auto-round

PTQ-Level Efficiency, QAT-Level Accuracy | 训练后量化的效率,量化感知训练的精度

Owner
intel (organization)
Stars
Stars: 1,698
Forks
Forks: 196
Language
Python
License
Apache-2.0
Created
2024
Topics
int4quantizationroundingtransformersvllmmxfp4nvfp4ggufsglangllms
Tier
Beta (700 to 1,999 ★) What this tier means
View on GitHub

More repos by intel

All 187 repos by intel

Nearby in Python

All Python repos