microsoft/VPTQ
View on GitHubVPTQ, A Flexible and Extreme low-bit quantization algorithm
- Stars
- 681
- Forks
- 53
- Open beginner issues
- 0
- Indexed issues
- 26
- Dominant language
- Python
- License
- MIT
- Last GitHub push
- Apr 25, 2025
- Latest indexed
- Sep 19, 2026
- Contributing guide
- No contributing guide
- Code of conduct
- Code of conduct
- Beginner labels
- No beginner labels indexed
- PR merge metrics
- No merged PRs in 30d
-
Difficulty 4/5 3-5 days Newbie friendliness 35/100
-
Difficulty 5/5 Over a week Newbie friendliness 20/100
-
Large PPL Fluctuations in VPTQ 4.05-bit Quantization Despite Fixed Random Seed and Identical Setup Open
Difficulty 5/5 Over a week Newbie friendliness 25/100
-
Difficulty 3/5 1-2 days Newbie friendliness 50/100
-
Difficulty 5/5 Over a week Newbie friendliness 10/100
-
qwen3 support Open
Difficulty 5/5 Over a week Newbie friendliness 25/100
-
Difficulty 4/5 3-5 days Newbie friendliness 35/100
-
gemma-3 support Open
-
Difficulty 5/5 Over a week Newbie friendliness 15/100
-
DeepSeek-R1 support Opennew models
microsoft/VPTQ#174 · 11 comments · 1 reaction · 1 assignee ·
-
alogrithm enhancement question
Difficulty 5/5 Over a week Newbie friendliness 20/100
-
bug question
Difficulty 4/5 3-5 days Newbie friendliness 35/100
-
question
-
features
-
CPU support Openinference
-
Custom Model support Opennew models question
Difficulty 5/5 Over a week Newbie friendliness 25/100
-
Add evaluation codes Openenhancement
Difficulty 4/5 3-5 days Newbie friendliness 25/100
-
Add FP8/INT8 support Openalogrithm
-
alogrithm
-
inference
-
alogrithm new models
-
Add vLLM support Openinference
-
inference question
Difficulty 4/5 3-5 days Newbie friendliness 25/100
-
question
Difficulty 2/5 1-3 hours Newbie friendliness 38/100