Huawei AI-Solver Group
Huawei AI-Solver Group
新闻
研究论文
成员
联系
Wulong Liu
Latest
CMoE: Fast Carving of Mixture-of-Experts for Efficient LLM Inference
KVTuner: Sensitivity-Aware Layer-wise Mixed Precision KV Cache Quantization for Efficient and Nearly Lossless 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
Cite
×