作者位次 #4/6ACL 2026Poster· Natural Language Processing
L o PT : Lossless Parallel Tokenization Acceleration for Long Context Inference of Large Language Model
Wei Shao · Zheng Lingchao · Pengyu Wang · Peizhen Zheng · Li Jun · Yuwei Fan
摘要
Long context inference scenarios have become increasingly important for large language models, yet they introduce significant computational latency. While prior research has optimized long-sequence inference through operators, model architectures, and system frameworks, tokenization remains an ov...