"au:"Christopher Lott"" — arXiv2 Search

/ Date/ Name

/ Date/ Name

"au:"Christopher Lott"" — arXiv2 Search

Showing 1–7 of 7 results

/ Date/ Name

Apr 27, 2023Moccasin: Efficient Tensor Rematerialization for Neural Networks Feb 21, 2024Recursive Speculative Decoding: Accelerating LLM Inference via Sampling Without Replacement Apr 13, 2024On Speculative Decoding for Multimodal Large Language Models Jun 10, 2024How Efficient is LLM-Generated Code? A Rigorous & High-Standard Benchmark Jul 13, 2022Neural Topological Ordering for Computation Graphs Feb 29, 2024Direct Alignment of Draft Model for Speculative Decoding with Chat-Fine-Tuned LLMs Sep 22, 2025Spiffy: Multiplying Diffusion LLM Acceleration via Lossless Speculative Decoding