Skip to main content

​
Installation

pip install blindference-node
For GPU-accelerated local inference: 
pip install "blindference-node[gpu]"
For development (tests, linting): 
pip install "blindference-node[dev]"

​
Option 2: From Source

git clone https://github.com/baync180705/Blindference-node.git
cd Blindference-node
pip install -e .
For GPU support from source: 
pip install -e ".[gpu]"

​
Option 3: Docker

docker build -t blindference-node .
docker run -e BLF_KEY_PASSWORD=secure_password \
  -e BLF_ICL_ENDPOINT=https://icl.blindference.xyz \
  blindference-node run
Or use docker-compose: 
docker-compose up

​
System Requirements

​
Minimum (Mock Inference)

ResourceRequirement
Python3.10+
CPU1 core
RAM512MB
NetworkOutbound HTTPS
GPUNone
ResourceRequirement
Python3.11+
CPU2+ cores
RAM2GB
NetworkStable internet
TPMTPM 2.0 chip (for tier 1)

​
Optional (Local Model Inference)

ResourceRequirement
GPUNVIDIA with CUDA
VRAM4GB+
vLLMInstalled

​
Verify Installation

blindference-node --version
# Expected: blindference-node, version 0.3.0

​
Troubleshooting Installation

​
Issue: pip install fails with compilation errors

Cause: Missing system dependencies for cryptography or web3. Fix (Ubuntu/Debian): 
sudo apt-get update
sudo apt-get install -y python3-dev libssl-dev libffi-dev build-essential
Fix (macOS): 
brew install openssl libffi

​
Issue: blindference-node: command not found

Cause: pip installed to a location not in your PATH. Fix: 
# Find the binary
python -m site --user-base
# Add to PATH:
export PATH="$PATH:$(python -m site --user-base)/bin"
Or use: 
python -m blindference_node.cli --help

​
Issue: GPU inference fails with CUDA not available

Cause: vLLM requires CUDA but GPU drivers are missing. Fix: 
# Check CUDA availability
python -c "import torch; print(torch.cuda.is_available())"

# If False, install NVIDIA drivers and CUDA toolkit
# Or run without GPU:
BLF_SUPPORTED_MODELS=qwen2.5-7b blindference-node init