IST-DASLab/gptq
gptq
Code for the ICLR 2023 paper "GPTQ: Accurate Post-training Quantization of Generative Pretrained Transformers".
Builder
IST-DASLab
IST-DASLab • individual
Stars
2,284
Using upstream star count
Forks
194
Using upstream fork count
Open Issues
0
Activity Score
0/100
0 commits in 30d
Created
Oct 19, 2022
Project creation date
README Summary
GPTQ is a post-training quantization method for Generative Pretrained Transformers that achieves accurate 4-bit quantization without requiring retraining. The repository contains the implementation of the GPTQ algorithm presented at ICLR 2023, which can compress large language models while maintaining their performance. It provides efficient quantization techniques specifically designed for transformer architectures.
AI Dev Skills
Unmapped
Tags
Taxonomy
Deployment Context
Modalities
Skill Areas
Recent Activity
Updated 2 years ago
7 Days
0
30 Days
0
90 Days
0
Quality
research- Quality
- high
- Maturity
- research
Categories
PM Skills
Languages
Timeline
- Project created
- Oct 19, 2022
- Forked
- Mar 22, 2026
- Your last push
- 2 years ago
- Upstream last push
- 2 years ago
- Tracked since
- Mar 27, 2024
Similar Repos
pgvector cosine similarity · $0
Loading…