Training-free speculative decoding for ONNX Runtime and Hugging Face PyTorch models
-
Updated
Jul 14, 2026 - Python
Training-free speculative decoding for ONNX Runtime and Hugging Face PyTorch models
(Re)-implementation of "Prompt Lookup Decoding" by Apoorv Saxena, with extended ideas from LLMA Decoding.
Speculative Decoding on Bandwidth-Bound Hardware
To associate your repository with the prompt-lookup-decoding topic, visit your repo's landing page and select "manage topics."