StructPrune: Structured Global Pruning asymptotics with $\mathcal{O}(\sqrt{N})$ GPU Memory
"结构化剪枝" 相关文章
StructPrune: Structured Global Pruning asymptotics with $\mathcal{O}(\sqrt{N})$ GPU Memory
PrunedLoRA: Robust Gradient-Based structured pruning for Low-rank Adaptation in Fine-tuning
2SSP: A Two-Stage Framework for Structured Pruning of LLMs
Pruning Large Language Models by Identifying and Preserving Functional Networks
Application-Specific Component-Aware Structured Pruning of Deep Neural Networks via Soft Coefficient Optimization
告别卡脖子，华为黑科技破局！昇腾推理加速1.6倍打破LLM降智魔咒
告别卡脖子，华为黑科技破局！昇腾推理加速1.6倍打破LLM降智魔咒
小而强，英伟达剪枝、蒸馏出 Llama-3.1-Minitron 4B AI 模型
