vllm-project/vllm

[Feature][Cleanup]: Unify `vllm.utils.flashinfer` and `vllm.model_executor.layers.quantization.utils.flashinfer_utils`

Open

#31,414 创建于 2025年12月27日

在 GitHub 查看
 (7 评论) (0 反应) (0 负责人)Python (80,034 star) (16,816 fork)batch import
feature requestgood first issuehelp wanted

描述

🚀 The feature, motivation and pitch

its confusing to have both

Alternatives

No response

Additional context

No response

Before submitting a new issue...

  • Make sure you already searched for relevant issues, and asked the chatbot living at the bottom right corner of the documentation page, which can answer lots of frequently asked questions.

贡献者指南

技术栈
python
领域
backend
议题类型
refactor
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
3
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
half day
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
active
清晰度议题是否清楚说明期望改动、验收标准和下一步。
mostly clear
前置要求
Basic Python knowledgeFamiliarity with vLLM structureUnderstanding of flashinfer
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
40
研究方向
Review the two files `vllm/utils/flashinfer.py` and `vllm/model executor/layers/quantization/utils/flashinfer utils.py`. Identify common functions and propose a unified module. Ensure all imports are updated and no functionality breaks. Consider creating a new file and deprecating the old ones.