作者位次 #7/11HPCA 2026Oral· High-Performance Computer Architecture
Characterizing Cloud-Native LLM Inference at Bytedance and Exposing Optimization Challenges and Opportunities for Future AI Accelerators
Jingwei Cai · Dehao Kong · Hantao Huang · Zishan Jiang · Zixuan Ma · Qingyu Guo · Zhenxing Zhang · Guiming Shi · Mingyu Gao · Kaisheng Ma · Minghui Yu