Posts by Collection

Channel-Aware Mixed-Precision Quantization for Efficient Long-Context Inference

Published in ICLR 2026, 2026

Chengxi Liao, Zeyi Wen

Download Paper

DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models

Published in DAC 2026, 2026

Youliang Huang, Xinhao Huang, Chengxi Liao, Zeyi Wen

Download Paper

Dovetail: Enabling FP4 KV Cache for Efficient LLM Serving on FP8-Capable GPUs

Preprint, 2026

Chengxi Liao, Yilin Liu, Ruijia Yang, Zeyi Wen

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

Download Paper

DSAA 2042: Computer Architecture and Systems

Teaching Assistant, The Hong Kong University of Science and Technology (Guangzhou), 2025

Teaching Assistant for DSAA 2042, Computer Architecture and Systems, Fall 2025.

DSAA 3032: Introduction to High-Performance and Parallel Computing

Teaching Assistant, The Hong Kong University of Science and Technology (Guangzhou), 2026

Teaching Assistant for DSAA 3032, Introduction to High-Performance and Parallel Computing, Summer 2026.