vllm-project/llm-compressor

State-of-the-art LLM compression, built for production inference with vLLM

3.9k
Stars
696
Forks
67.9
Radar Score
Rising
Momentum

Scoring Breakdown

Impact83.2
Velocity53.7
Health63.4

Growth Metrics

7-Day Stars
+19
30-Day Stars
+65
Acceleration
0.88x
Language
Python

Why it ranks

Strong momentum — adoption is accelerating week over week.

LLM Frameworks · inference engineTop 81% globallyLast push 1d ago+19 stars / 7d+65 stars / 30d
View on GitHub