Book
Open access
Jul 2026
Three Birds, One Stone: Fast, Accurate-aware and Cost-Efficient Accelerator for Ternary LLM
T-ACE is presented, a Ternary Accuracy-aware Compute Engine that enables efficient ternary LLM inference under PTQ by jointly designing the data representation and execution pipeline and integrates on-the-fly decoding and scaling directly into the ternary GEMM pipeline.
Wonseok Jung, Junseok Kang, Sangwon Shin et al.
· International Conference on... · 0 citations