Getting started¶
One install gets you the whole stack. Pick the entry point that matches how you want to work — Python, or plain language.
Install¶
That pulls the engine (sweep-solver) and the toolkit built on it:
the YAML task runner (sweepx.tasks), the losses, networks, optimizers
and I/O it uses (sweepx.loss, sweepx.nn,
sweepx.opt, sweepx.io) and the natural-language layer
(sweepx.agent). The engine imports as
sweep (the name sweep was taken on PyPI, hence sweep-solver), the toolkit as sweepx.<module>:
Python 3.10+. The wheel ships a prebuilt CUDA core, so the native-CUDA backend
(impl='c') runs straight after install with any PyTorch version: no nvcc, no
compile step, just an NVIDIA GPU and driver. The pure-Python torch / JAX backends
need nothing else.
Your first forward model¶
import numpy as np, torch
from sweep.equations import Acoustic
from sweep.propagator.torch import PropTorch
from sweep.signal import ricker
dev = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
solver = PropTorch(Acoustic(device=dev), shape=(96, 128), dh=10.0, dt=2e-3, device=dev)
wavelet = ricker(np.arange(600) * 2e-3 - 0.12, f=10.0).astype(np.float32)
sources = np.array([[64, 2]], dtype=np.int64)
receivers = np.array([[[ix, 4] for ix in range(0, 128, 2)]], dtype=np.int64)
vp = torch.full((96, 128), 2000.0, device=dev) # (nz, nx)
gather = solver(wavelet, sources, receivers, models=[vp]) # (1, nt, nrec, 1)
Your first gradient¶
Every propagator call is an autograd node, so inversion is ordinary PyTorch. Record data for a model with a faster box, then take the gradient of the misfit at the constant model:
vp_true = vp.clone()
vp_true[48:58, 32:96] = 2300.0
with torch.no_grad():
obs = solver(wavelet, sources, receivers, models=[vp_true])
vp = vp.clone().requires_grad_(True)
pred = solver(wavelet, sources, receivers, models=[vp])
loss = 0.5 * (pred - obs).pow(2).sum()
loss.backward() # vp.grad is a plain torch Tensor — feed any optimizer
…or say it in plain language¶
sweepx.agent turns a sentence into a validated run, driven by a local
LLM (Ollama on a Mac, vLLM on a GPU node):
Where to go next¶
-
Equations, propagators, backends, boundary-saving — and over thirty runnable notebooks under Examples.
-
Production FWI / LSRTM from one YAML file: specs, CLI, multi-GPU, data IO.
-
Misfit functions for inversion — L2 to envelope, phase and optimal transport.
-
Implicit FWI: the model as a network — SIREN, hash encoding, priors.
-
SEG-Y to gathers: header index, data plans, prefetched reads, models, geometry.
-
FWI optimizers: L-BFGS, truncated Newton / Gauss-Newton, Adam, Shampoo / SOAP, preconditioners.
-
Tools, the web UI, and how to point it at any OpenAI-compatible LLM.
-
Every equation, propagator, and operator, documented from source.