Huawei AI-Solver Group
Huawei AI-Solver Group
新闻
研究论文
成员
联系
Xing Li
Latest
KVTuner: Sensitivity-Aware Layer-wise Mixed Precision KV Cache Quantization for Efficient and Nearly Lossless LLM Inference
TrimR: Verifier-based Training-Free Thinking Compression for Efficient Test-Time Scaling
Cite
×