Showing cs.DCShow all
3 papers · 1 filter
cs.DC2025
PUSHtap: PIM-based In-Memory HTAP with Unified Data Storage Format
Yilong Zhao, Mingyu Gao, Huanchen Zhang +5
Hybrid transaction/analytical processing (HTAP) is an emerging database paradigm that supports both online transaction processing (OLTP) and online analytical processing (OLAP) wor…
cs.DC2025
MILLION: Mastering Long-Context LLM Inference Via Outlier-Immunized KV Product Quantization
Zongwu Wang, Peng Xu, Fangxin Liu +7
Large language models (LLMs) are increasingly utilized for complex tasks requiring longer context lengths, with some models supporting up to 128K or 1M tokens. This trend, however,…
cs.DC2024
TokenRing: An Efficient Parallelism Framework for Infinite-Context LLMs via Bidirectional Communication
Zongwu Wang, Fangxin Liu, Mingshuai Li +1
Efficient parallelization of Large Language Models (LLMs) with long sequences is essential but challenging due to their significant computational and memory demands, particularly s…