LA

llm-awq

Model Optimization·infrastructure·open·#893 of 944·-138·Rising

55.9

Low

High confidence

[MLSys 2024 Best Paper Award] AWQ: Activation-aware Weight Quantization for LLM Compression and Acceleration

Pillar Breakdown

Adoption

35%

46.0

Maintenance

30%

55.2

Friction

20%

99.9

Ecosystem

15%

36.6

Momentum

0.52Rising
7d change +1.19
High confidence

In Model Optimization

Ranked #15 of 16

Similar Tools