-
Notifications
You must be signed in to change notification settings - Fork 1.6k
Clarify CUDA/CuPy install requirements in docs (#8106) #8983
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Open
Shizoqua
wants to merge
1
commit into
Project-MONAI:dev
Choose a base branch
from
Shizoqua:docs/8106-cuda-cupy-install
base: dev
Could not load branches
Branch not found: {{ refName }}
Loading
Could not load tags
Nothing to show
Loading
Are you sure you want to change the base?
Some commits from the old base branch may be removed from the timeline,
and old review comments may become outdated.
Open
Changes from all commits
Commits
File filter
Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
There are no files selected for viewing
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
🎯 Functional Correctness | 🟡 Minor | ⚡ Quick win
🧩 Analysis chain
🏁 Script executed:
Repository: Project-MONAI/MONAI
Length of output: 7481
🌐 Web query:
PyTorch official installation guide pip CUDA_PATH manual download CUDA wheel selector locally install💡 Result:
To install PyTorch with CUDA support, the official and recommended method is to use the interactive installer on the PyTorch website, which generates the correct pip or Conda command based on your operating system, Python version, and CUDA version [1][2][3]. For scenarios where you need to manually manage or download specific CUDA-enabled wheels, follow these steps: Official Installation Guide The primary resource for installation is the PyTorch Get Started page (https://pytorch.org/get-started/locally/) [1][3]. The page provides an interactive selector that detects your system preferences and provides the precise installation command [1][4]. Manual Wheel Selection and Local Install If you need to install a specific wheel file (e.g., for offline installation or custom environments), you can access the PyTorch binary repository directly [5][6]: 1. Repository Access: All PyTorch wheels are hosted at https://download.pytorch.org/whl/ [6]. 2. Selecting CUDA Versions: Within this repository, directories are organized by CUDA version (e.g., /cu126/ for CUDA 12.6) [5][6]. 3. Finding the Wheel: Navigate to the sub-directory matching your desired CUDA version and the torch package [5]. You can identify the correct file based on your Python version (e.g., cp312 for Python 3.12) and your system architecture (e.g., linux_x86_64, win_amd64) [7]. 4. Installing Locally: Once you have the direct URL to the.whl file, you can install it using pip: pip install <URL_TO_WHEEL_FILE> [8] Alternative: Index-URL Installation If you have a local environment where you want to force pip to use the official PyTorch binary repository for dependencies, you can specify the index-url: pip install torch==+cu --index-url https://download.pytorch.org/whl/cu [8] Environment Variables While
CUDA_PATHis a standard system environment variable used by NVIDIA drivers, PyTorch binaries downloaded from the official repository generally include their own CUDA runtime libraries, meaning you do not typically need to configureCUDA_PATHfor the pre-compiled pip packages to function, provided your system has a compatible NVIDIA driver installed [9][4]. If you are building PyTorch from source, you may need to ensure yourPATHandCMAKE_PREFIX_PATHare configured correctly to point to your local CUDA installation [9][10].Citations:
Reword the PyTorch/CUDA install step.
docs/source/installation.md:38-42The pip flow should point users to PyTorch’s CUDA selector or wheel index; prebuilt pip wheels already include the CUDA runtime, so “download CUDA manually” and
CUDA_PATHare misleading here.🤖 Prompt for AI Agents