“decoder”

REST

REST: Retrieval-Based Speculative Decoding

Medusa

Medusa: Simple Framework for Accelerating LLM Generation with Multiple Decoding Heads

vec2text

utilities for decoding deep representations (like sentence embeddings) back to text

EAGLE

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

atlas

Pure Rust Inference Engine

Context-Engine

Context-Engine MCP - Agentic Context Compression Suite