Skip to content
Blueprint

← All articles · Dashboard

Python runtime

The optional Python sidecar Blueprint uses for the heavy bits — LoRA training, LLMLingua compression, vLLM, TensorRT-LLM. Opt-in feature by feature.

3 min read

What it is

llama.cpp does inference. But other parts of the LLM stack — fine-tuning a LoRA, compressing prompts with LLMLingua, running vLLM or TensorRT-LLM — are Python-side ecosystems. Bundling all of PyTorch + transformers + every accelerator wheel into the desktop installer would push the download past 2 GB even for users who don't need them.

Solution: an opt-in Python sidecar. Blueprint ships uv (~5 MB, astral.sh's Rust-based Python toolchain) and on first use of a Python-side feature, runs uv python install + uv pip install <packages> into a venv under ~/.blueprint/python/.

The user picks which features to install from the Python runtime card on the Dashboard. Nothing happens until they opt in.

The feature catalog

FeatureMarginal sizeNeeds GPU?Provides
Python core230 MBnouv-managed Python 3.11 + minimal libs (fastapi, uvicorn, requests)
LLMLingua250 MBnoprompt compression sidecar
PyTorch + CUDA 12.x2,500 MByes (NVIDIA)the GPU compute stack everything below depends on
LoRA training800 MByestransformers, peft, accelerate, bitsandbytes, trl, datasets
vLLM engine1,200 MByesPagedAttention-based serving
TensorRT-LLM engine2,000 MByesNVIDIA's compiled-engine path

Sizes are MARGINAL — what each feature adds on top of what's already installed. Pick "LoRA training" and the card automatically queues "Python core" + "PyTorch + CUDA 12.x" as dependencies.

How to install

  1. Dashboard → Python runtime card.
  2. Pick the feature. The card shows the total disk impact (the feature itself + any dependencies it pulls in).
  3. Click Install. Blueprint downloads uv if not yet present, runs uv python install, then uv pip install <packages> in the managed venv. Logs stream into the install panel.
  4. The card flips to Installed when done. The corresponding feature card elsewhere on the Dashboard (TrainCard, Compress card, the vLLM engine option) becomes active.

Total install time depends on download speed and CPU — PyTorch + CUDA is the slowest step (~5-15 min on most boxes).

How to uninstall

Same card → Uninstall. Removes the packages from the venv but keeps the feature available to reinstall later. To wipe the entire Python install, the Reset Blueprint data action in the Maintain tab nukes ~/.blueprint/python/ along with everything else.

Common pitfalls

  • Trying to use vLLM / TensorRT-LLM without a CUDA GPU: these features require an NVIDIA card with a working CUDA driver. Apple Silicon and AMD aren't supported by the upstream Python packages yet. The card warns; the install still proceeds; runtime fails later.
  • uv's first-time Python download failing: uv pulls Python from astral's CDN. Corporate proxies sometimes block. Workaround: set https_proxy env vars before launching Blueprint.
  • Disk full halfway through: PyTorch + CUDA is 2.5 GB. If ~/.blueprint/ is on a small partition, the install fails partway with no clean rollback. Free space before installing.

Need help with this in production?

Inspire AI Lab runs LLM optimization engagements end-to-end using Blueprint. If you'd rather hand the work to us instead of running it yourself, book a 30-minute review.