logo
Free, unlimited AI code reviews that run on commit
git-lrc git-lrc GitHub Install Now We'd appreciate a star git-lrc - Free, unlimited AI code reviews that run on commit | Product Hunt git-lrc - Free, unlimited AI code reviews that run on commit | Product Hunt
How to install deepseek-ai/DeepEP. Official installation instructions. Project installation guide. Framework or library installation. Build installation instructions. How to setup and install from GitHub. Installation steps and setup instructions. Official docs and installation instructions GitHub.

deepseek-ai/DeepEP Installation Guide

How to install deepseek-ai/DeepEP. Official project installation instructions and setup guide.

Automated Install (Recommended)

Quick installation instructions for deepseek-ai/DeepEP. This is the fastest way to complete project installation and setup.

Install via curl

curl -fsSL https://hexmos.com/ipm-install | bash && 
ipm i deepseek-ai/DeepEP
or

Install via npx

npx @hexmos/ipm i deepseek-ai/DeepEP

Prerequisites

Ampere, Hopper GPUs, or architectures with SM90 PTX ISA support

hardware

Python

programming-language

Version: 3.8+

CUDA

toolkit

Version: 11.0+ for SM80, 12.3+ for SM90

PyTorch

library

Version: 2.1+

NVLink

hardware-interface

Version: required for intranode communication

RDMA network

network-interface

Version: required for internode communication

NVSHMEM

library

Version: required

Manual Installation Methods

Manual installation instructions. How to install from GitHub source.

Install from source

git clone https://github.com/deepseek-ai/DeepEP

cd DeepEP

export NVSHMEM_DIR=/path/to/installed/nvshmem

python setup.py build

ln -s build/lib.linux-x86_64-cpython-38/deep_ep_cpp.cpython-38-x86_64-linux-gnu.so

NVSHMEM_DIR=/path/to/installed/nvshmem python setup.py install