2 papers
cs.DC2025
Injecting Adrenaline into LLM Serving: Boosting Resource Utilization and Throughput via Attention Disaggregation
Yunkai Liang, Zhangyu Chen, Pengfei Zuo +3
In large language model (LLM) serving systems, executing each request consists of two phases: the compute-intensive prefill phase and the memory-intensive decoding phase. To preven…
cs.AR2019
Efficient Similarity-aware Compression to Reduce Bit-writes in Non-Volatile Main Memory for Image-based Applications
Zhangyu Chen, Yu Hua, Pengfei Zuo +2
Image bitmaps have been widely used in in-memory applications, which consume lots of storage space and energy. Compared with legacy DRAM, non-volatile memories (NVMs) are suitable…