Long Cheng

Sr Architect@NVIDIA·中国·OpenReview

研究方向

LLM Compiler · Large Language Model · AI Domain-specific Architecture · Heterogeneous Programming · Mix-precision Computing · High-performance Computing · Computational Fluid Dynamics

4.0

Online Pseudo-average Shifting Attention(PASA) for Robust Low-precision LLM Inference: Algorithms, Numerical Analysis and Performance

合作者 (12)