quivers 0.10.0

A functional probabilistic programming language that compiles to PyTorch.

Quivers

A functional probabilistic programming language for PyTorch.

Tutorial · Examples · Guides · API · Semantics

---

Quivers is a functional probabilistic programming language for PyTorch. The surface will look familiar if you have used Pyro, NumPyro, Stan, or PyMC. But it has a few distinguishing features:

• Programs are first-class composable typed values. A program has a domain, codomain, algebra, and effect signature (! Sample, Score, Marginal, Pure), checked at compile time. Programs compose with >>, parallel-compose with @, change base across algebras with change_base, and marginalize discrete latents with marginalize z : K <- ... in { ... }.
• Shared substrate for inference, deduction, and structural compression. A CKY parser in a deduction { atoms ... rule ... } block, a transformer-as-encoder over a signature { ... } block, and a Bayesian regression all compile to the same underlying semantics, with the same composition operators, and can therefore compose with each other.
• Algebra-parametric semantics. Programs can be parameterized by eleven built-in or user-defined algebras. Homomorphisms between algebras are values you can transport models along, with the laws checked at compile time.

It also has some features you are used to from other PPLs:

• An inference toolkit. Forty distribution families. SVI with nine automatic guides (mean-field through full-rank multivariate normal, low-rank, mixture, IAF, neural-spline flow, AutoDAIS) and four objectives (ELBO, IWAE, Renyi, VR-IWAE) with reparameterized, score-function, sticking-the-landing, and DReG gradient estimators. NUTS and HMC with dual-averaging step-size adaptation and Welford mass-matrix adaptation.
• An analysis toolkit. Static introspection of compiled programs (per-step algebra, chain depth, intermediate shape, source mapping); algebra-aware, saturation-free initialization recipes that adapt to whichever value algebra a program is parameterized over; compile-time diagnostics flagging latents whose default initialization would saturate the active algebra.
• Diagnostics and model comparison. ArviZ ecosystem integration: posteriors from any inference method (NUTS, HMC, or SVI) export to ArviZ for trace plots, rank plots, ESS, and $\hat R$. PSIS-LOO (Pareto-smoothed importance-sampling leave-one-out cross-validation) for ranking competing models; posterior-predictive checks against user-defined test statistics; LOO-PIT for calibration.
• A mixed-effect model API. A brms-style formula frontend for mixed-effect regression compiles formulas to typed QVR programs through a bidirectional lens, with pandas / polars dataframes as the input surface and R-canonical conventions (orthogonal polynomials, R-style transforms in the formula evaluation namespace) as defaults. The emitted QVR is inspectable, so a formula-fitted model is a starting point you can hand-edit rather than a closed black box.
• Interactive tooling out of the box. qvr repl is a GHCi-style four-pane Textual TUI with live syntax highlighting, env browser, file-watcher auto-reload, command palette, and meta-commands (:type, :info, :browse, :edit, :save, :watch, …). qvr-lsp is a full LSP 3.17 language server (hover, definition, references, document symbols, semantic tokens, completion, formatting, live diagnostics) that VS Code, Cursor, Zed, and Neovim consume out of the box. A Jupyter kernel (qvr-kernel install) drives the same elaborator from notebooks.

Quick start

pip install quivers

object Item : 100

program regression : Item -> Item ! Sample, Score
    sigma  <- HalfNormal(1.0)
    beta_0 <- Normal(0.0, 5.0)
    beta_1 <- Normal(0.0, 2.0)
    let mu = beta_0 + beta_1 * x
    observe y <- Normal(mu, sigma)
    return y

export regression

from quivers.dsl import loads
from quivers.inference import AutoNormalGuide, ELBO, SVI
import torch

program = loads(open("regression.qvr").read())
model   = program.morphism
guide   = AutoNormalGuide(model, observed_names={"y"})
optim   = torch.optim.Adam(guide.parameters(), lr=1e-2)
svi     = SVI(model, guide, optim, ELBO())
for _ in range(2000):
    svi.step(x_data, {"y": y_data})

The full walkthrough is in the tutorial.

Documentation

• Tutorial: the QVR DSL tutorial walks probabilistic-programming users from linear regression to inference-algorithm choice with PyMC, NumPyro, and Stan equivalents shown side-by-side, while the Python API tutorial covers the typed categorical surface.
• Examples gallery: 36 end-to-end models covering regression, latent-variable, state-space, language models, seq2seq, and formal grammars.
• Conceptual guides: feature-area deep dives.
• API reference: the typed Python surface.
• Denotational semantics: the meaning of every well-typed program in a $\mathcal{V}$-enriched symmetric monoidal closed category.

Installation

pip install quivers

From source:

git clone https://github.com/FACTSlab/quivers
cd quivers
pip install -e ".[dev]"

Requirements: Python 3.14+, PyTorch 2.0+, didactic 0.7.1+, panproto 0.47.3+, panproto-grammars-all 0.47.3+.

Optional extras:

pip install 'quivers[repl]'    # Textual TUI, prompt_toolkit, rich, ipykernel
pip install 'quivers[lsp]'     # pygls language server
pip install 'quivers[repl,lsp]'  # both

After installing [repl] you can drop into the interactive type explorer:

qvr repl path/to/model.qvr

After installing [lsp] you have qvr-lsp on your PATH; the vscode-qvr and zed-extension-qvr extensions auto-discover it.

Contributing

See CONTRIBUTING.md. Issues and pull requests welcome at github.com/FACTSlab/quivers.

Acknowledgments

This project was developed by Aaron Steven White at the University of Rochester with support from the National Science Foundation (NSF-BCS-2237175 CAREER: Logical Form Induction, NSF-BCS-2040831 Computational Modeling of the Internal Structure of Events). It was architected and implemented with the assistance of Claude Code.

License

MIT. See LICENSE.