Reading the repo
Reading the repo
Assembly instructions
DeepInfer: High-performance, large-scale inference framework for DeepSeek models
Saved setup from 12 h ago
Will it work on my device?
Then run bash setup.sh. It stops at the first error and is safe to run again. Servers and tests aren't started; it lists them at the end. Read it first.
Needs Git: xcode-select --install. The repo uses git submodules, so the clone fetches them too.
git clone --recurse-submodules https://github.com/deepseek-ai/DeepInfer.git cd DeepInfer
Python >=3.12
brew install python@3.12
python -m venv .venv source .venv/bin/activate pip install -r requirements.txt pip install -r requirements-dev.txt
pytest
Before building DeepInfer, please create and activate an empty Python 3.12 environment.
# Use `ascend` instead for the Ascend platform
# Keep it exported in the environment where you run DeepInfer
export DEEPINFER_ACCELERATOR=nvidia
./build.sh
The default checkpoint, deepseek-ai/DeepSeek-V4.1-Flash-1017, is
downloaded into the Hugging Face cache on the first run; set DEEPINFER_HF_MODEL_DIR=/path/to/DeepSeek-V4.1-Flash-1017 to
run from a local copy instead.
python examples/offline_inference.py
See examples for details.
No reports for macOS yet.
Claude reads the 8 key files and writes a step-by-step guide for macOS. Once written, it's saved for everyone.