It Takes Two to Tango: Accelerating Code Generation via Cache-Inspired Hierarchical Speculative Decoding
收藏官方服务：
资源简介：
This repository contains 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”.
提供机构：
Zenodo创建时间：
2026-03-25
