『EP5: Speculative Decoding with Nadav Timor』のカバーアート

EP5: Speculative Decoding with Nadav Timor

EP5: Speculative Decoding with Nadav Timor

無料で聴く

ポッドキャストの詳細を見る

このコンテンツについて

We discussed the inference optimization technique known as Speculative Decoding with a world class researcher, expert, and ex-coworker of the podcast hosts: Nadav Timor.

Papers and links:

  • Accelerating LLM Inference with Lossless Speculative Decoding Algorithms for Heterogeneous Vocabularies, Timor et al, ICML 2025, https://arxiv.org/abs/2502.05202
  • Distributed Speculative Inference (DSI): Speculation Parallelism for Provably Faster Lossless Language Model Inference, Timor et al, ICLR, 2025, https://arxiv.org/abs/2405.14105
  • Fast Inference from Transformers via Speculative Decoding, Leviathan et al, 2022, https://arxiv.org/abs/2502.05202
  • FindPDFs - https://huggingface.co/datasets/HuggingFaceFW/finepdfs

まだレビューはありません