Hacktoberfest 2026:維護者為十月標記出來的 issue,仍然開放、適合新手。 瀏覽 Hacktoberfest issue

lmdeploy[all]==0.3.0安装是否只能在linux下进行

未關閉
#630 0 則留言 0 個 reaction 已指派 0 人 在 GitHub 檢視

還沒有人認領這個 Issue。

評估

難度
5/5
預估耗時
一週以上
新手友好度
20/100
Issue 類型
缺陷
描述清晰度
需要釐清
活躍度
停滯
技術堆疊
python, pytorch

研究方向

issue 中沒有指定原始檔案或測試。首先檢查 lmdeploy 0.3.0 的相依性中繼資料和 Windows 安裝路徑,重點關注 triton 要求;完成的標準是確定 Windows 是否受支援,並記錄或實作一條受支援的安裝路徑。

由索引模型根據 Issue 內容生成。

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

主要語言
Python
星號
2k
分支
1.5k
PR 合併指標
30 天內沒有已合併 PR

環境準備

我們還沒有檢查這個專案的環境設定檔。先看它的 README,通用步驟見我們的新手貢獻指南。

從這裡開始

  1. 先讀完整個 Issue,再讀專案的貢獻指南。
  2. 在 Issue 下留言說明你要接手 —— 這能避免兩個人做同樣的事。
  3. Fork 儲存庫,在一個分支上完成修改。
  4. 送出 Pull Request,並在描述裡引用這個 Issue 編號。

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 寄到你的電子郵件信箱

精選適合新手參與的 GitHub issue 摘要。