Showing 2026Show all
2 papers · 1 filter
cs.CL2026
Pruning via Causal Attribution Preserves Reasoning Performance in Large Language Models
Amogh Sheth, Biruk Assefa, Yi Wen Huang +2
Large language models (LLMs) excel at multi-step reasoning but incur substantial inference cost. We introduce Causal Attribution Pruning (CAP), a training-free method that identifi…
cs.DC2026
AscendCraft: Automatic Ascend NPU Kernel Generation via DSL-Guided Transcompilation
Zhongzhen Wen, Shudi Shao, Zhong Li +4
The performance of deep learning models critically depends on efficient kernel implementations, yet developing high-performance kernels for specialized accelerators remains time-co…