Channel-Aware Mixed-Precision Quantization for Efficient Long-Context Inference
Published in ICLR 2026, 2026
Chengxi Liao, Zeyi Wen
Publications
You can also find my articles on my Google Scholar profile.
Conference Papers
Strong Drafts Need Compact Memories: Long-Context Speculative Decoding with Compressed KV Cache
Published in Findings of EMNLP 2026, 2026
Tong Yuan, Chengxi Liao, Zeyi Wen
DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models
Published in DAC 2026, 2026
Youliang Huang, Xinhao Huang, Chengxi Liao, Zeyi Wen
Preprint
Dovetail: Enabling FP4 KV Cache for Efficient LLM Serving on FP8-Capable GPUs
Preprint, 2026
Chengxi Liao, Yilin Liu, Ruijia Yang, Zeyi Wen