Hacktoberfest 2026:维护者为十月标记出来的 issue,仍然开放、适合新手。 浏览 Hacktoberfest issue

lmdeploy[all]==0.3.0安装是否只能在linux下进行

未关闭
#630 0 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看

还没有人认领这个 Issue。

评估

难度
5/5
预计耗时
一周以上
新手友好度
20/100
Issue 类型
缺陷
描述清晰度
需要澄清
活跃度
停滞
技术栈
python, pytorch

调研方向

issue 中没有指定源文件或测试。首先检查 lmdeploy 0.3.0 的依赖元数据和 Windows 安装路径,重点关注 triton 要求;完成的标准是确定 Windows 是否受支持,并记录或实现一条受支持的安装路径。

由索引模型根据 Issue 内容生成。

描述

你好,lmdeploy[all]==0.3.0安装是否只能在linux下进行?windows下报这个错,然后我从网上找到的triton都是linux版本的

(lmdeploy) PS D:\pythonworkspace\MyPET> pip install lmdeploy[all]==0.3.0
Looking in indexes: https://mirrors.aliyun.com/pypi/simple
Collecting lmdeploy==0.3.0 (from lmdeploy[all]==0.3.0)
Downloading https://mirrors.aliyun.com/pypi/packages/2e/7c/b616d7485c4b81b2fe0a6a734548697d25293d5468210aafbf371d24a790/lmdeploy-0.3.0-cp310-cp310-win_amd64.whl (56.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 56.3/56.3 MB 5.3 MB/s eta 0:00:00
Requirement already satisfied: fastapi in d:\program\anaconda\envs\lmdeploy\lib\site-packages (from lmdeploy==0.3.0->lmdeploy[all]==0.3.0) (0.110.1)
Requirement already satisfied: fire in d:\program\anaconda\envs\lmdeploy\lib\site-packages (from lmdeploy==0.3.0->lmdeploy[all]==0.3.0) (0.6.0)
Requirement already satisfied: mmengine-lite in d:\program\anaconda\envs\lmdeploy\lib\site-packages (from lmdeploy==0.3.0->lmdeploy[all]==0.3.0) (0.10.3)
Requirement already satisfied: numpy in d:\program\anaconda\envs\lmdeploy\lib\site-packages (from lmdeploy==0.3.0->lmdeploy[all]==0.3.0) (1.26.4)
Collecting peft<=0.9.0 (from lmdeploy==0.3.0->lmdeploy[all]==0.3.0)
Downloading https://mirrors.aliyun.com/pypi/packages/08/87/3e7eb34ac06d3f4ac72e2302e9e69bef12247a8a627c59a4d8a498135727/peft-0.9.0-py3-none-any.whl (190 kB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 190.9/190.9 kB 3.9 MB/s eta 0:00:00
Requirement already satisfied: pillow in d:\program\anaconda\envs\lmdeploy\lib\site-packages (from lmdeploy==0.3.0->lmdeploy[all]==0.3.0) (10.3.0)
Requirement already satisfied: protobuf in d:\program\anaconda\envs\lmdeploy\lib\site-packages (from lmdeploy==0.3.0->lmdeploy[all]==0.3.0) (4.25.3)
Requirement already satisfied: pydantic>2.0.0 in d:\program\anaconda\envs\lmdeploy\lib\site-packages (from lmdeploy==0.3.0->lmdeploy[all]==0.3.0) (2.6.4)
Requirement already satisfied: pynvml in d:\program\anaconda\envs\lmdeploy\lib\site-packages (from lmdeploy==0.3.0->lmdeploy[all]==0.3.0) (11.5.0)
Requirement already satisfied: safetensors in d:\program\anaconda\envs\lmdeploy\lib\site-packages (from lmdeploy==0.3.0->lmdeploy[all]==0.3.0) (0.4.2)
Requirement already satisfied: sentencepiece in d:\program\anaconda\envs\lmdeploy\lib\site-packages (from lmdeploy==0.3.0->lmdeploy[all]==0.3.0) (0.2.0)
Requirement already satisfied: shortuuid in d:\program\anaconda\envs\lmdeploy\lib\site-packages (from lmdeploy==0.3.0->lmdeploy[all]==0.3.0) (1.0.13)
Requirement already satisfied: tiktoken in d:\program\anaconda\envs\lmdeploy\lib\site-packages (from lmdeploy==0.3.0->lmdeploy[all]==0.3.0) (0.6.0)
Collecting torch<=2.1.2,>=2.0.0 (from lmdeploy==0.3.0->lmdeploy[all]==0.3.0)
Downloading https://mirrors.aliyun.com/pypi/packages/16/bf/2ba0f0f7c07b9a14c027e181e44c58824e13f7352607ed32db18321599a2/torch-2.1.2-cp310-cp310-win_amd64.whl (192.3 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 192.3/192.3 MB 7.3 MB/s eta 0:00:00
Collecting transformers<=4.38.2,>=4.33.0 (from lmdeploy==0.3.0->lmdeploy[all]==0.3.0)
Downloading https://mirrors.aliyun.com/pypi/packages/b6/4d/fbe6d89fde59d8107f0a02816c4ac4542a8f9a85559fdf33c68282affcc1/transformers-4.38.2-py3-none-any.whl (8.5 MB)
━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━ 8.5/8.5 MB 7.7 MB/s eta 0:00:00
INFO: pip is looking at multiple versions of lmdeploy to determine which version is compatible with other requirements. This could take a while.
ERROR: Could not find a version that satisfies the requirement triton<=2.2.0,>=2.1.0 (from lmdeploy) (from versions: none)
ERROR: No matching distribution found for triton<=2.2.0,>=2.1.0

主要语言
Python
星标
2k
派生
1.5k
PR 合并指标
30 天内没有已合并 PR

贡献指南

这个仓库没有索引到贡献指南

从这里开始

  1. 先读完整个 Issue,再读项目的贡献指南。
  2. 在 Issue 下留言说明你要接手 —— 这能避免两个人做同样的事。
  3. Fork 仓库,在一个分支上完成修改。
  4. 提交 Pull Request,并在描述里引用这个 Issue 编号。

InternLM/Tutorial 的其他 Issue

查看 InternLM/Tutorial 的全部 Issue

相似的 Issue

更多 Python Issue

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。