Huawei AI-Solver Group
Huawei AI-Solver Group
新闻
研究论文
成员
联系
Xianzhi Yu
Latest
CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference
PreMoe: Lightening MoEs on Constrained Memory by Expert Pruning and Retrieval
TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling
FuseGPT: Learnable Layers Fusion of Generative Pre-trained Transformers
Cite
×