[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"project-1174":3},{"id":4,"name":5,"fullName":6,"owner":7,"repo":5,"description":8,"homepage":8,"htmlUrl":8,"language":9,"languages":8,"totalLinesOfCode":8,"stars":10,"forks":11,"watchers":12,"openIssues":13,"contributorsCount":14,"subscribersCount":14,"size":14,"stars1d":15,"stars7d":16,"stars30d":17,"stars90d":14,"forks30d":14,"starsTrendScore":18,"compositeScore":19,"rankGlobal":8,"rankLanguage":8,"license":20,"archived":21,"fork":21,"defaultBranch":22,"hasWiki":23,"hasPages":23,"topics":24,"createdAt":8,"pushedAt":8,"updatedAt":25,"readmeContent":26,"aiSummary":27,"trendingCount":14,"starSnapshotCount":14,"syncStatus":28,"lastSyncTime":29,"discoverSource":30},1174,"ddtree","liranringel\u002Fddtree","liranringel",null,"Python",370,22,7,3,0,4,8,35,12,56.59,"MIT License",false,"master",true,[],"2026-06-12 04:00:08","\u003Ch1 align=\"center\">DDTree\u003C\u002Fh1>\n\n\u003Cp align=\"center\">\n  Official implementation of \u003Cstrong>DDTree (Diffusion Draft Tree)\u003C\u002Fstrong> from\n  \u003Cem>Accelerating Speculative Decoding with Block Diffusion Draft Trees\u003C\u002Fem>.\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  Liran Ringel, Yaniv Romano\n\u003C\u002Fp>\n\n\u003Cp align=\"center\">\n  \u003Ca href=\"https:\u002F\u002Fliranringel.github.io\u002Fddtree\u002F\">🌐 Project Page\u003C\u002Fa>\n   | \n  \u003Ca href=\"https:\u002F\u002Farxiv.org\u002Fabs\u002F2604.12989\">📄 Paper\u003C\u002Fa>\n\u003C\u002Fp>\n\n## Setup\n\nThis codebase is intended for a CUDA-enabled PyTorch environment.\n\n```bash\npip install -r requirements.txt\n```\n\n## Run Experiments\n\n```bash\nbash run_benchmark.sh\n```\n\nThis produces benchmark outputs in `runs\u002F` and logs in `logs\u002F`.\n\n## Reproduce Paper Artifacts\n\nGenerate the plots:\n\n```bash\npython3 plot_results.py\n```\n\nGenerate the LaTeX table:\n\n```bash\npython3 make_latex_table.py\n```\n\n## Citation\n\n```bibtex\n@article{ringel2026ddtree,\n  title={Accelerating Speculative Decoding with Block Diffusion Draft Trees},\n  author={Ringel, Liran and Romano, Yaniv},\n  journal={arXiv preprint arXiv:2604.12989},\n  year={2026}\n}\n```\n","DDTree是一个用于加速推测解码过程的工具，基于名为“Block Diffusion Draft Trees”的方法实现。该项目主要通过CUDA支持的PyTorch环境运行，利用了扩散草稿树技术来提高解码效率。它适用于需要高效处理序列生成任务的场景，如自然语言处理中的文本生成或机器翻译等应用。此外，DDTree还提供了实验运行脚本和结果可视化工具，方便研究者复现论文中的实验数据与图表。",2,"2026-06-11 02:42:08","CREATED_QUERY"]