Home/Data & Retrieval/REST

REST

FasterDecoding/REST

REST: Retrieval-Based Speculative Decoding

GitHub

GraphCanon updated 3w · GitHub synced 3w

220 stars17 forksLast push 5mo C Apache-2.0

Decision brief

REST is a retrieval-based speculative decoding tool implemented in C, designed for use cases that demand efficiency and fine-grained control over inference processes through its distinctive approach.

Good fit when

- When you need high performance and are willing to work with the C language for customization and optimization.
- If your project can benefit from retrieval-based speculative decoding, offering unique insights into model predictions based on past responses.

Avoid when

- Avoid if your team lacks proficiency in C programming as this may lead to an overhead in developing and maintaining the tool.
- Not recommended for projects where flexibility with commonly used high-level languages like Python is essential, as REST primarily relies on lower-level language capabilities.

Observed Jul 12, 2026 · Source: enrich:decision_facts

REST alternatives Trust report

Verify the decision

Maintenance and security

Full trust report

Maintenance: Slowing (148d since push); As of 3w
Provenance: Not a fork · Organization account; As of 3w
Security (OSV): 2 low (2 low); As of 1mo

Public GitHub metadata and optional OSV scans. Signals, not a guarantee. Trust methodology.

Install

git clone https://github.com/FasterDecoding/REST

Similar tools

Same-category neighbours. No typed graph edges are catalogued for this tool yet.

llama.cpp

LLM inference in C/C++

123k★

RAG_Techniques

Showcases advanced techniques for Retrieval-Augmented Generation (RAG) systems with detailed notebook tutorials.

29k★

airllm

AirLLM 70B inference with single 4GB GPU

24k★

Evidence and technical details

Sourced facts, taxonomy, compatibility claims, README excerpt, and machine-readable endpoints.

Overview

A tool for retrieval-based speculative decoding using the C programming language, introduced in NAACL 2024.

Capability facts

Languages: c
Source: github.language · Aug 1, 2026

Compatibility

Sourced claims from the README excerpt - not unsourced marketing copy.

Python runtimePython

Source: README excerpt (regex_v1, Aug 1, 2026)

conda create -n rest python=3.9

Source link

README

Installation

conda create -n rest python=3.9
conda activate rest
pip3 install -r requirements.txt # pay attention to Pytorch CUDA version
pip3 install DraftRetriever/wheels/draftretriever-0.1.0-cp39-cp39-manylinux_2_34_x86_64.whl

For agents

This page has a .md twin and JSON over the API.

/tools/fasterdecoding-rest.md GET /api/graphcanon/tools/fasterdecoding-rest GET /api/graphcanon/graph?tool=fasterdecoding-rest