mlx-nufft 0.1.1__tar.gz

mlx_nufft-0.1.1/LICENSE

@@ -0,0 +1,216 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.
+
+   Copyright 2026 Martin Lachaine
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

mlx_nufft-0.1.1/NOTICE

@@ -0,0 +1,28 @@
+mlx-nufft
+Copyright 2026 Martin Lachaine
+
+mlx-nufft is an independent implementation of non-uniform fast Fourier
+transforms (types 1, 2, 3, in 1/2/3 dimensions) for Apple GPUs via Metal/MLX.
+Its algorithms and internal structure follow the FINUFFT and cuFINUFFT
+libraries (Apache License 2.0, Copyright The Simons Foundation, Inc.) — the
+exponential-of-semicircle kernel, the spreading/deconvolution structure, and
+the type-3 construction — which were also used as the reference implementation
+and numerical oracle during development. mlx-nufft was written from the
+published methods with the FINUFFT source as a reference; it does not include
+or redistribute FINUFFT source code.
+
+If you use this software, please cite the underlying methods:
+
+  A. H. Barnett, J. Magland, and L. af Klinteberg, "A parallel nonuniform
+  fast Fourier transform library based on an exponential of semicircle
+  kernel," SIAM J. Sci. Comput. 41(5), C479-C504 (2019). arXiv:1808.06736
+
+  A. H. Barnett, "Aliasing error of the exp(beta sqrt(1-z^2)) kernel in the
+  nonuniform fast Fourier transform," Appl. Comput. Harmon. Anal. 51, 1-16
+  (2021). arXiv:2001.09405
+
+  Y. Shih, G. Wright, J. Anden, J. Blaschke, and A. H. Barnett, "cuFINUFFT:
+  a load-balanced GPU library for general-purpose nonuniform FFTs," PDSEC
+  (IPDPS workshops) 2021. arXiv:2102.08463
+
+FINUFFT: https://github.com/flatironinstitute/finufft

mlx_nufft-0.1.1/PKG-INFO

@@ -0,0 +1,202 @@
+Metadata-Version: 2.4
+Name: mlx-nufft
+Version: 0.1.1
+Summary: Non-uniform FFTs (types 1/2/3, dims 1/2/3) on Apple GPUs via Metal/MLX
+Author: Martin Lachaine
+Project-URL: Homepage, https://github.com/martinlachaine/mlx-nufft
+Project-URL: Repository, https://github.com/martinlachaine/mlx-nufft
+Project-URL: Issues, https://github.com/martinlachaine/mlx-nufft/issues
+Project-URL: Changelog, https://github.com/martinlachaine/mlx-nufft/blob/main/CHANGELOG.md
+Keywords: nufft,nonuniform-fft,fft,apple-silicon,metal,mlx,gpu
+Classifier: Development Status :: 4 - Beta
+Classifier: Intended Audience :: Science/Research
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: MacOS
+Classifier: Programming Language :: Python :: 3
+Classifier: Topic :: Scientific/Engineering
+Classifier: Topic :: Scientific/Engineering :: Mathematics
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+License-File: NOTICE
+Requires-Dist: mlx==0.31.2
+Requires-Dist: numpy>=2.0
+Provides-Extra: dev
+Requires-Dist: finufft==2.5.1; extra == "dev"
+Requires-Dist: scipy>=1.14; extra == "dev"
+Dynamic: license-file
+
+# mlx-nufft — non-uniform FFTs on Apple GPUs (Metal/MLX)
+
+[![tests](https://github.com/martinlachaine/mlx-nufft/actions/workflows/ci.yml/badge.svg)](https://github.com/martinlachaine/mlx-nufft/actions/workflows/ci.yml)
+[![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
+[![Python](https://img.shields.io/badge/python-3.11%2B-blue.svg)](pyproject.toml)
+[![Platform](https://img.shields.io/badge/platform-Apple%20silicon-lightgrey.svg)](#install)
+[![Backend: MLX](https://img.shields.io/badge/backend-MLX%200.31.2-orange.svg)](https://github.com/ml-explore/mlx)
+
+mlx-nufft computes non-uniform fast Fourier transforms — types 1, 2 and 3, in
+dimensions 1, 2 and 3 — on Apple-silicon GPUs via Metal/MLX, with a drop-in
+mirror of the `finufft` Python API. It runs an fp32 GPU pipeline with the
+precision-critical coordinate setup performed in double precision at plan time
+("crit64"), so it reaches fp64-grade accuracy on hardware that has no native
+double precision.
+
+> **Paper:** [`mlx-nufft.pdf`](mlx-nufft.pdf) — a technical report
+> describing the method, accuracy, and performance (types 1/2/3 in 1/2/3D, the
+> crit64 precision mechanism, and M1 / M5 Max benchmarks).
+> Pin a tagged release rather than tracking `main`.
+
+## Install
+
+Requires an Apple-silicon Mac (Metal/MLX). Install the release directly from
+GitHub (not yet on PyPI):
+
+```bash
+pip install "git+https://github.com/martinlachaine/mlx-nufft.git@v0.1.0"
+```
+
+then `import mlx_nufft`. Dependencies are pinned (notably `mlx==0.31.2`).
+
+For development — running the test/benchmark harness, which uses CPU `finufft`
+and `scipy` as references:
+
+```bash
+git clone https://github.com/martinlachaine/mlx-nufft && cd mlx-nufft
+uv venv --python 3.13 .venv
+uv pip install -p .venv/bin/python -e ".[dev]"
+```
+
+Verify the install — run the full correctness suite (each test compares against
+CPU `finufft` and/or an exact direct-summation oracle):
+
+```bash
+.venv/bin/python harness/run_tests.py
+```
+
+It prints a per-test pass/fail summary and exits non-zero on any failure. The
+optional VkFFT backend test reports `SKIP` unless the bridge in
+`vkfft_bridge/` is built.
+
+## Quickstart
+
+A complete, copy-paste-runnable 2-D type-1 transform (M nonuniform points →
+`N1 × N2` uniform Fourier modes):
+
+```python
+import numpy as np
+import mlx_nufft as finufft
+
+rng = np.random.default_rng(0)
+M, N1, N2 = 100_000, 256, 256
+x = rng.uniform(-np.pi, np.pi, M)                          # coords in [-pi, pi)
+y = rng.uniform(-np.pi, np.pi, M)
+c = rng.standard_normal(M) + 1j * rng.standard_normal(M)   # source strengths
+
+fk = finufft.nufft2d1(x, y, c, (N1, N2), eps=1e-6)         # -> (256, 256) complex
+```
+
+A fuller runnable script (basic call, plan reuse, and a self-check against an
+exact direct DFT — no `finufft` install needed) is in
+[`examples/quickstart.py`](examples/quickstart.py):
+
+```bash
+python examples/quickstart.py
+```
+
+## Usage
+
+Drop-in `finufft` API (same call surface):
+
+```python
+import mlx_nufft as finufft
+
+fk = finufft.nufft2d1(x, y, c, (N1, N2), eps=1e-6)   # all nufft{1,2,3}d{1,2,3}
+plan = finufft.Plan(1, (N1, N2), n_trans=8, eps=1e-6)
+plan.setpts(x, y)
+fk = plan.execute(c)
+```
+
+Native plan classes — `Type3Plan` (type-3 engine) and `Type1PlanND` /
+`Type2PlanND` (dims 1–3):
+
+```python
+from mlx_nufft import Type3Plan
+
+# plan once (geometry-dependent setup cached), execute per call
+plan = Type3Plan((x1, x2, x3), (s1, s2, s3), eps=1e-5, isign=+1)
+f = plan.execute(c)            # f[k] = sum_j c[j] exp(i*isign * s_k . x_j)
+```
+
+`Type1PlanND` also offers a batched multi-strength execute over one shared
+point spread, and a cheap re-point of a fixed-mode-box plan to new coordinates:
+
+```python
+from mlx_nufft import Type1PlanND
+
+plan = Type1PlanND((x, y), (N1, N2), eps=1e-5, isign=+1)
+fk = plan.execute_batch(cs)               # cs: (B, P) over the same points -> (B, N1, N2)
+plan.set_sources((x2, y2), backend="gpu") # re-point without recompiling kernels
+fk2 = plan.execute(c2)
+```
+
+The double-single phase primitive is also exposed standalone, for callers with
+a large-magnitude fp64 phase that cannot be reduced mod 2π in fp32 but want the
+`cos`/`sin` on the GPU:
+
+```python
+from mlx_nufft import expi, EXPI_MAX_PHASE
+
+z = expi(phi)                    # device complex64 e^{i*phi}, phi an fp64 array
+z = expi([a, b, c], isign=-1)    # phase summed in double-single: e^{-i*(a+b+c)}
+```
+
+An optional VkFFT-Metal FFT backend is selectable for the type-3 slab path
+(`Type3Plan(..., fft_backend="vkfft")`, requires building the bridge in
+`vkfft_bridge/`); MLX's FFT is the default. `vkfft_available()` reports whether
+the bridge is built.
+
+## Documented differences from `finufft`
+
+- Computation is fp32-grade (crit64): `eps` below 1e-6 clamps with a warning;
+  complex128 inputs are accepted and returned but transformed at fp32 grade.
+- `modeord=1` (FFT ordering) is not implemented.
+- 1D/2D type 3 run as degenerate slices of the 3D type-3 kernel.
+- Plans hold points as plan state (`setpts`); `out=` and multi-vector
+  `(n_trans, ...)` shapes mirror finufft, and `Plan.execute_adjoint`
+  (finufft 2.5) is supported for all three types.
+
+## Layout
+
+- `mlx_nufft/` — the library: `gpu_t3.py` (type-3 engine), `nd.py`
+  (`Type1PlanND`/`Type2PlanND`), `types12.py`, `dfmath.py` (the `expi` /
+  double-single primitive), `sizing.py` (kernel/grid sizing), `api.py` (the
+  `finufft`-compatible surface), `vkfft_backend.py`.
+- `examples/` — runnable, dependency-light usage examples
+  (`quickstart.py`).
+- `harness/` — correctness tests (`test_*.py`), the suite runner
+  (`run_tests.py`), the acceptance/benchmark runner, and the CPU-reference
+  oracle.
+- `vkfft_bridge/` — optional VkFFT-Metal backend build.
+
+## Development and validation
+
+mlx-nufft is AI-assisted, human-directed research software. Its scope, numerical
+requirements, validation strategy, acceptance criteria, and release decisions
+are the author's; generative AI tools accelerated implementation, refactoring,
+test scaffolding, and documentation.
+
+Generated code was not trusted by default. Every component was validated against
+independent references — CPU FINUFFT, exact direct-summation oracles on small
+problems, transform-convention and adjoint checks, full dimension/type coverage,
+dtype/device behavior, and API-parity tests (see `harness/`).
+
+The author is responsible for the released software — its design, limitations,
+and maintenance. Known limitations and hardware assumptions are documented;
+corrections are welcome via the issue tracker.
+
+## License & citation
+
+Apache-2.0 (see `LICENSE`). mlx-nufft is an independent implementation that
+follows the FINUFFT/cuFINUFFT algorithms and was validated against FINUFFT;
+see `NOTICE` for attribution and the methods papers to cite, and `CITATION.cff`
+to cite mlx-nufft itself.

mlx_nufft-0.1.1/README.md

@@ -0,0 +1,174 @@
+# mlx-nufft — non-uniform FFTs on Apple GPUs (Metal/MLX)
+
+[![tests](https://github.com/martinlachaine/mlx-nufft/actions/workflows/ci.yml/badge.svg)](https://github.com/martinlachaine/mlx-nufft/actions/workflows/ci.yml)
+[![License: Apache 2.0](https://img.shields.io/badge/License-Apache_2.0-blue.svg)](LICENSE)
+[![Python](https://img.shields.io/badge/python-3.11%2B-blue.svg)](pyproject.toml)
+[![Platform](https://img.shields.io/badge/platform-Apple%20silicon-lightgrey.svg)](#install)
+[![Backend: MLX](https://img.shields.io/badge/backend-MLX%200.31.2-orange.svg)](https://github.com/ml-explore/mlx)
+
+mlx-nufft computes non-uniform fast Fourier transforms — types 1, 2 and 3, in
+dimensions 1, 2 and 3 — on Apple-silicon GPUs via Metal/MLX, with a drop-in
+mirror of the `finufft` Python API. It runs an fp32 GPU pipeline with the
+precision-critical coordinate setup performed in double precision at plan time
+("crit64"), so it reaches fp64-grade accuracy on hardware that has no native
+double precision.
+
+> **Paper:** [`mlx-nufft.pdf`](mlx-nufft.pdf) — a technical report
+> describing the method, accuracy, and performance (types 1/2/3 in 1/2/3D, the
+> crit64 precision mechanism, and M1 / M5 Max benchmarks).
+> Pin a tagged release rather than tracking `main`.
+
+## Install
+
+Requires an Apple-silicon Mac (Metal/MLX). Install the release directly from
+GitHub (not yet on PyPI):
+
+```bash
+pip install "git+https://github.com/martinlachaine/mlx-nufft.git@v0.1.0"
+```
+
+then `import mlx_nufft`. Dependencies are pinned (notably `mlx==0.31.2`).
+
+For development — running the test/benchmark harness, which uses CPU `finufft`
+and `scipy` as references:
+
+```bash
+git clone https://github.com/martinlachaine/mlx-nufft && cd mlx-nufft
+uv venv --python 3.13 .venv
+uv pip install -p .venv/bin/python -e ".[dev]"
+```
+
+Verify the install — run the full correctness suite (each test compares against
+CPU `finufft` and/or an exact direct-summation oracle):
+
+```bash
+.venv/bin/python harness/run_tests.py
+```
+
+It prints a per-test pass/fail summary and exits non-zero on any failure. The
+optional VkFFT backend test reports `SKIP` unless the bridge in
+`vkfft_bridge/` is built.
+
+## Quickstart
+
+A complete, copy-paste-runnable 2-D type-1 transform (M nonuniform points →
+`N1 × N2` uniform Fourier modes):
+
+```python
+import numpy as np
+import mlx_nufft as finufft
+
+rng = np.random.default_rng(0)
+M, N1, N2 = 100_000, 256, 256
+x = rng.uniform(-np.pi, np.pi, M)                          # coords in [-pi, pi)
+y = rng.uniform(-np.pi, np.pi, M)
+c = rng.standard_normal(M) + 1j * rng.standard_normal(M)   # source strengths
+
+fk = finufft.nufft2d1(x, y, c, (N1, N2), eps=1e-6)         # -> (256, 256) complex
+```
+
+A fuller runnable script (basic call, plan reuse, and a self-check against an
+exact direct DFT — no `finufft` install needed) is in
+[`examples/quickstart.py`](examples/quickstart.py):
+
+```bash
+python examples/quickstart.py
+```
+
+## Usage
+
+Drop-in `finufft` API (same call surface):
+
+```python
+import mlx_nufft as finufft
+
+fk = finufft.nufft2d1(x, y, c, (N1, N2), eps=1e-6)   # all nufft{1,2,3}d{1,2,3}
+plan = finufft.Plan(1, (N1, N2), n_trans=8, eps=1e-6)
+plan.setpts(x, y)
+fk = plan.execute(c)
+```
+
+Native plan classes — `Type3Plan` (type-3 engine) and `Type1PlanND` /
+`Type2PlanND` (dims 1–3):
+
+```python
+from mlx_nufft import Type3Plan
+
+# plan once (geometry-dependent setup cached), execute per call
+plan = Type3Plan((x1, x2, x3), (s1, s2, s3), eps=1e-5, isign=+1)
+f = plan.execute(c)            # f[k] = sum_j c[j] exp(i*isign * s_k . x_j)
+```
+
+`Type1PlanND` also offers a batched multi-strength execute over one shared
+point spread, and a cheap re-point of a fixed-mode-box plan to new coordinates:
+
+```python
+from mlx_nufft import Type1PlanND
+
+plan = Type1PlanND((x, y), (N1, N2), eps=1e-5, isign=+1)
+fk = plan.execute_batch(cs)               # cs: (B, P) over the same points -> (B, N1, N2)
+plan.set_sources((x2, y2), backend="gpu") # re-point without recompiling kernels
+fk2 = plan.execute(c2)
+```
+
+The double-single phase primitive is also exposed standalone, for callers with
+a large-magnitude fp64 phase that cannot be reduced mod 2π in fp32 but want the
+`cos`/`sin` on the GPU:
+
+```python
+from mlx_nufft import expi, EXPI_MAX_PHASE
+
+z = expi(phi)                    # device complex64 e^{i*phi}, phi an fp64 array
+z = expi([a, b, c], isign=-1)    # phase summed in double-single: e^{-i*(a+b+c)}
+```
+
+An optional VkFFT-Metal FFT backend is selectable for the type-3 slab path
+(`Type3Plan(..., fft_backend="vkfft")`, requires building the bridge in
+`vkfft_bridge/`); MLX's FFT is the default. `vkfft_available()` reports whether
+the bridge is built.
+
+## Documented differences from `finufft`
+
+- Computation is fp32-grade (crit64): `eps` below 1e-6 clamps with a warning;
+  complex128 inputs are accepted and returned but transformed at fp32 grade.
+- `modeord=1` (FFT ordering) is not implemented.
+- 1D/2D type 3 run as degenerate slices of the 3D type-3 kernel.
+- Plans hold points as plan state (`setpts`); `out=` and multi-vector
+  `(n_trans, ...)` shapes mirror finufft, and `Plan.execute_adjoint`
+  (finufft 2.5) is supported for all three types.
+
+## Layout
+
+- `mlx_nufft/` — the library: `gpu_t3.py` (type-3 engine), `nd.py`
+  (`Type1PlanND`/`Type2PlanND`), `types12.py`, `dfmath.py` (the `expi` /
+  double-single primitive), `sizing.py` (kernel/grid sizing), `api.py` (the
+  `finufft`-compatible surface), `vkfft_backend.py`.
+- `examples/` — runnable, dependency-light usage examples
+  (`quickstart.py`).
+- `harness/` — correctness tests (`test_*.py`), the suite runner
+  (`run_tests.py`), the acceptance/benchmark runner, and the CPU-reference
+  oracle.
+- `vkfft_bridge/` — optional VkFFT-Metal backend build.
+
+## Development and validation
+
+mlx-nufft is AI-assisted, human-directed research software. Its scope, numerical
+requirements, validation strategy, acceptance criteria, and release decisions
+are the author's; generative AI tools accelerated implementation, refactoring,
+test scaffolding, and documentation.
+
+Generated code was not trusted by default. Every component was validated against
+independent references — CPU FINUFFT, exact direct-summation oracles on small
+problems, transform-convention and adjoint checks, full dimension/type coverage,
+dtype/device behavior, and API-parity tests (see `harness/`).
+
+The author is responsible for the released software — its design, limitations,
+and maintenance. Known limitations and hardware assumptions are documented;
+corrections are welcome via the issue tracker.
+
+## License & citation
+
+Apache-2.0 (see `LICENSE`). mlx-nufft is an independent implementation that
+follows the FINUFFT/cuFINUFFT algorithms and was validated against FINUFFT;
+see `NOTICE` for attribution and the methods papers to cite, and `CITATION.cff`
+to cite mlx-nufft itself.

mlx_nufft-0.1.1/mlx_nufft/__init__.py

@@ -0,0 +1,48 @@
+"""mlx-nufft: non-uniform FFTs on Apple GPUs (Metal, via MLX).
+
+Drop-in mirror of the `finufft` Python package's interface:
+
+    import mlx_nufft as finufft
+    fk = finufft.nufft2d1(x, y, c, (N1, N2), eps=1e-6)   # types 1/2/3, dims 1/2/3
+    plan = finufft.Plan(1, (N1, N2), eps=1e-6)
+    plan.setpts(x, y)
+    fk = plan.execute(c)
+
+plus the native plan classes:
+
+    from mlx_nufft import Type3Plan
+    plan = Type3Plan((x1, x2, x3), (s1, s2, s3), eps=1e-5, isign=+1)
+    f = plan.execute(c)          # f[k] = sum_j c[j] exp(i*isign*s_k.x_j)
+
+Precision model (see REPORT.md): fp32 GPU pipeline with the precision-
+critical setup (coordinate rescale, pre/post phases) in fp64 at plan time
+('crit64', the default). Plans cache all geometry-dependent state, so
+fixed-geometry workloads pay setup once and execute() per call.
+"""
+
+from .gpu_t3 import GpuT3Plan as Type3Plan
+from .types12 import Type1Plan, Type2Plan
+from .nd import Type1PlanND, Type2PlanND
+from .dfmath import expi, EXPI_MAX_PHASE
+from .sizing import kernel_params, next235even
+from .api import (Plan,
+                  nufft1d1, nufft1d2, nufft1d3,
+                  nufft2d1, nufft2d2, nufft2d3,
+                  nufft3d1, nufft3d2, nufft3d3)
+
+
+def vkfft_available():
+    """True if the optional VkFFT-Metal FFT backend (fft_backend='vkfft') is
+    built and loadable — see vkfft_bridge/build.sh."""
+    from . import vkfft_backend
+    return vkfft_backend.available()
+
+
+__version__ = "0.1.1"
+__all__ = ["Type3Plan", "Type1Plan", "Type2Plan",
+           "Type1PlanND", "Type2PlanND", "Plan",
+           "nufft1d1", "nufft1d2", "nufft1d3",
+           "nufft2d1", "nufft2d2", "nufft2d3",
+           "nufft3d1", "nufft3d2", "nufft3d3",
+           "kernel_params", "next235even", "vkfft_available",
+           "expi", "EXPI_MAX_PHASE"]