Loading listing…
awq-quantization
Security scan passedActivation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss.
Part of AI Research Skills (Orchestra)Pack · 98 skills
by Orchestra-Research· AI & agentsUnclaimed · Yours? Claim it
What awq-quantization does
About
Activation-aware weight quantization for 4-bit LLM compression with 3x speedup and minimal accuracy loss. Use when deploying large models (7B-70B) on limited GPU memory, when you need faster inference than GPTQ with better accuracy preservation, or for instruction-tuned and multimodal models. MLSys 2024 Best Paper Award winner.
Install awq-quantization
More from AI & agents
Skills people install alongside awq-quantization.
