3 papers
cs.LG2026
One QK Channel, Many Sources: Guarding Low-Precision Attention Collapse
Shuxiao Xie, Shuyang Xie, Yuan Cao +3
A bfloat16 transformer can train normally for many steps and then collapse abruptly. Distinct low-precision errors can trigger the same failure, leaving unclear whether each source…
cs.LG2026
KernelBand: Steering LLM-based Kernel Optimization via Hardware-Aware Multi-Armed Bandits
Dezhi Ran, Shuxiao Xie, Mingfang Ji +9
High-performance GPU kernels are critical for efficient LLM serving, yet their optimization remains a bottleneck requiring deep system expertise. While code LLMs show promise in ge…
cs.DC2026
PARD: Enhancing Goodput for Inference Pipeline via Proactive Request Dropping
Zhixin Zhao, Yitao Hu, Simin Chen +8
Modern deep neural network (DNN) applications integrate multiple DNN models into inference pipelines with stringent latency requirements for customized tasks. To mitigate extensive…