⚡ Build your chatbot within minutes on your favorite device; offer SOTA compression techniques for LLMs; run LLMs efficiently on Intel Platforms⚡

Official Implementation of EAGLE-1 (ICML'24), EAGLE-2 (EMNLP'24), and EAGLE-3 (NeurIPS'25).

scalable and robust tree-based speculative decoding algorithm

Code for "LayerSkip: Enabling Early Exit Inference and Self-Speculative Decoding", ACL 2024

[COLM 2024] TriForce: Lossless Acceleration of Long Sequence Generation with Hierarchical Speculative Decoding

Model compression toolkit engineered for enhanced usability, comprehensiveness, and efficiency.

LLM Inference on consumer devices

[ICML 2025] |TokenSwift: Lossless Acceleration of Ultra Long Sequence Generation

[NeurIPS'23] Speculative Decoding with Big Little Decoder

Implementation of the paper Fast Inference from Transformers via Speculative Decoding, Leviathan et al. 2023.

[ICLR 2025] SWIFT: On-the-Fly Self-Speculative Decoding for LLM Inference Acceleration

[ICML 2025] Reward-guided Speculative Decoding (RSD) for efficiency and effectiveness.

Codes for our paper "Speculative Decoding: Exploiting Speculative Execution for Accelerating Seq2seq Generation" (EMNLP 2023 Findings)

Official implementation of CEED-VLA: Consistency Vision-Language-Action Model with Early-Exit Decoding.

Pretty and simple to use implementation of speculative decoding algorithm eagle which is extrapolation algorithm for greater language model efficiency 🦅

Official Implementation of SAM-Decoding: Speculative Decoding via Suffix Automaton

Official Implementation of LANTERN (ICLR'25) and LANTERN++(ICLRW-SCOPE'25)

Official Implementation of "GRIFFIN: Effective Token Alignment for Faster Speculative Decoding"[NeurIPS 2025]

Accelerating LLM inference with techniques like speculative decoding, quantization, and kernel fusion, focusing on implementing state-of-the-art research papers.

Unofficial implementation of Token Recycling self-speculative decoding method.