Installing Narwhal from PyPI¶
narwhal-inference installs the narwhal Python package and six commands for local development, engine launch, attestation, profiling, preflight and routing. The package requires Linux and Python 3.11 or newer.
Install the package in a virtual environment:
python3 -m venv .venv
source .venv/bin/activate
python -m pip install narwhal-inference
narwhal-serve --version
narwhal --help
Verifying the installation¶
Expected narwhal-serve --version output:
narwhal --helplists the six installed commands.- Each command accepts
--versionbefore its operational arguments. - Each
--versioninvocation exits with status 0.
For each deployment:
- Record the version with the fleet configuration, engine image, and profiles.
- Pin the approved version on every router host.
Before serving requests¶
Qualify these production inputs by following Deploying a fleet:
- separately provisioned vLLM engines with NIXL, or SGLang engines with Mooncake
- engine attestation
- a fleet configuration
- measured profiles
Installing from a source checkout¶
In a repository checkout, make setup installs Narwhal and its development dependencies into .venv.
If --version prints narwhal-inference unknown (distribution metadata unavailable), run python -m pip install -e ..