5 papers · 1 filter
PreMoE: Proactive Inference for Efficient Mixture-of-Experts
Zehua Pei, Ying Zhang, Hui-Ling Zhen +6
Mixture-of-Experts (MoE) models offer dynamic computation, but are typically deployed as static full-capacity models, missing opportunities for deployment-specific specialization.…
Analytical FFN-to-MoE Restructuring via Activation Pattern Analysis
Zehua Pei, Hui-Ling Zhen, Lancheng Zou +5
Scaling large language models (LLMs) improves performance but significantly increases inference costs, with feed-forward networks (FFNs) consuming the majority of computational res…
From Pruning to Grafting: Dynamic Knowledge Redistribution via Learnable Layer Fusion
Zehua Pei, Hui-Ling Zhen, Xianzhi Yu +3
Structured pruning of Generative Pre-trained Transformers (GPTs) offers a promising path to efficiency but often suffers from irreversible performance degradation due to the discar…
MOSS: Efficient and Accurate FP8 LLM Training with Microscaling and Automatic Scaling
Yu Zhang, Hui-Ling Zhen, Mingxuan Yuan +1
Training large language models with FP8 formats offers significant efficiency gains. However, the reduced numerical precision of FP8 poses challenges for stable and accurate traini…
MixPE: Quantization and Hardware Co-design for Efficient LLM Inference
Yu Zhang, Mingzi Wang, Lancheng Zou +4
Transformer-based large language models (LLMs) have achieved remarkable success as model sizes continue to grow, yet their deployment remains challenging due to significant computa…