Showing cs.DCShow all
2 papers · 1 filter
cs.DC2026
DPS: Dual-Mode Precision LLM Serving with Semi-Unified Memory
Xuan Truong Nguyen, Tien Son Pham, Tuan Duc Chu +2
Existing LLM serving systems virtualize and optimize KV-cache memory, but treat model-weight memory as fixed throughout execution. Recent work on multi-precision model representati…
cs.DC2026
PEAT: Pseudo-Error Assessment for GPU Kernel Validation in DNN Training
Xuan Truong Nguyen, Hong Quan Tran, Tuan Duc Chu +1
Deep neural networks (DNNs) are widely adopted in various fields, driving an emerging trend in developing software stacks associated with DNN training systems. For example, many co…