Login
Download
Skill UI
Browse and discover
7129+
curated skills
All
Development
Artificial Intelligence
Design & Creative
Product & Business
Data Science
Marketing
Soft Skills
Productivity
Engineering
Languages
Search
Kernel
, found
1
results
Default
Newest
Most Downloaded
AWQ Weight Quantization
awq-quantization
Orchestra-Research/AI-Research-SKILLs
353
Activation-aware weight quantization that compresses 7B-70B models to 4-bit with minimal accuracy loss, delivering ~3x inference speedups and memory reductions for constrained GPU deployments while integrating with vLLM and Marlin kernels.
View Details
1
Language
简体中文
English