2025 "autoregressive inference" Papers
2 papers found
CLOVER: Cross-Layer Orthogonal Vectors Pruning and Fine-Tuning
Fanxu Meng, Muhan Zhang
ICLR 2025posterarXiv:2411.17426
Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference
Nadav Timor, Jonathan Mamou, Daniel Korat et al.
ICLR 2025posterarXiv:2405.14105
7
citations