🧑🔬 Shang Yang — papers of 2024 — 2 papers, the most cited first2 papers · all years of Shang YangQServe: W4A8KV4 Quantization and System Co-design for Efficient LLM ServingMLSys 2025Yujun Lin, Haotian Tang, Shang Yang, et al.2024 · 120 citationsDuoAttention: Efficient Long-Context LLM Inference with Retrieval and Streaming HeadsarXiv:2410.10819Guangxuan Xiao, Jiaming Tang, Jingwei Zuo, et al.2024 · 114 citationsThis page in Markdown → https://md.research.elamur.ai/free/en/authors/shang-yang/year/2024/