It Takes Two to Tango: Accelerating Code Generation via Cache-Inspired Hierarchical Speculative Decoding

Anonymous

Description

This repository contains code and the distilled checkpoints of the draft models for CodeLlama-34b and Deepseek-Code-33b for the paper “It Takes Two to Tango: Accelerating Code Generation via Cache-Inspired Hierarchical Speculative Decoding”.CacheCoder.zip contains the source code of this research. checkpoints.zip contains the distilled weights of the draft model used in this research.

Citations (0)

Mentions (0)

Metrics

Dataset Index

0.4

FAIR Score

81%

Citations

0

Mentions

0

Metrics Over Time

Publication Details

DOI

Publisher

Zenodo

License

Creative Commons Attribution 4.0 International

Assigned Domain

Subfield

Artificial Intelligence

Field

Computer Science

Domain

Physical Sciences

Confidence Score

50%

Source

Scholar Data Model

Normalization Factors

FT

63.46

CTw

1.00

MTw

1.00