pyturboquant-cpu 0.1.0__tar.gz

pyturboquant_cpu-0.1.0/.github/DISCUSSION_TEMPLATE/announcements.yml

@@ -0,0 +1,10 @@
+title: Announcements
+body:
+  - type: textarea
+    id: welcome_text
+    attributes:
+      label: Welcome Text
+      description: Welcome text for this announcement.
+      placeholder: Write something here...
+    validations:
+      required: true

pyturboquant_cpu-0.1.0/.github/FUNDING.yml

@@ -0,0 +1 @@
+github: [ishandutta2007]

pyturboquant_cpu-0.1.0/.github/workflows/publish.yml

@@ -0,0 +1,38 @@
+name: Publish to PyPI
+
+on:
+  push:
+    tags:
+      - 'v*'
+  workflow_dispatch:
+
+jobs:
+  build-and-publish:
+    name: Build and publish Python distribution to PyPI
+    runs-on: ubuntu-latest
+    environment:
+      name: pypi
+      url: https://pypi.org/p/pyturboquant-cpu
+    permissions:
+      id-token: write  # IMPORTANT: mandatory for trusted publishing
+      contents: read
+    
+    steps:
+      - name: Checkout repository
+        uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: "3.x"
+
+      - name: Install build dependencies
+        run: python -m pip install --upgrade pip build
+
+      - name: Build a binary wheel and a source tarball
+        run: python -m build
+
+      - name: Publish package distribution to PyPI
+        uses: pypa/gh-action-pypi-publish@release/v1
+        with:
+          skip-existing: true

pyturboquant_cpu-0.1.0/.gitignore

@@ -0,0 +1,54 @@
+# Byte-compiled / optimized / DLL files
+__pycache__/
+*.py[cod]
+*$py.class
+
+# C extensions
+*.so
+
+# Distribution / packaging
+.Python
+build/
+develop-eggs/
+dist/
+downloads/
+eggs/
+.eggs/
+lib/
+lib64/
+parts/
+sdist/
+var/
+wheels/
+*.egg-info/
+.installed.cfg
+*.egg
+
+# Virtual environments
+.env
+.venv
+env/
+venv/
+ENV/
+
+# IDE
+.vscode/
+.idea/
+*.swp
+*.swo
+
+# Testing
+.pytest_cache/
+.coverage
+htmlcov/
+.tox/
+.nox/
+
+# mypy
+.mypy_cache/
+
+# Misc
+*.bk
+*.bak
+.DS_Store
+Thumbs.db

pyturboquant_cpu-0.1.0/LICENSE

@@ -0,0 +1,176 @@
+
+                                 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.
+
+      "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 the 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 the 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 any 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

pyturboquant_cpu-0.1.0/PKG-INFO

@@ -0,0 +1,170 @@
+Metadata-Version: 2.4
+Name: pyturboquant-cpu
+Version: 0.1.0
+Summary: CPU implementation of TurboQuant data-oblivious vector quantization (arXiv:2504.19874)
+Author: pyturboquant contributors
+License-Expression: Apache-2.0
+Project-URL: Homepage, https://github.com/pyturboquant/pyturboquant-cpu
+Project-URL: Documentation, https://github.com/pyturboquant/pyturboquant-cpu#readme
+Project-URL: Repository, https://github.com/pyturboquant/pyturboquant-cpu
+Project-URL: Issues, https://github.com/pyturboquant/pyturboquant-cpu/issues
+Keywords: vector-quantization,kv-cache,llm,compression,turboquant,quantization
+Classifier: Development Status :: 3 - Alpha
+Classifier: Intended Audience :: Developers
+Classifier: Intended Audience :: Science/Research
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Topic :: Scientific/Engineering :: Artificial Intelligence
+Classifier: Topic :: Scientific/Engineering :: Mathematics
+Requires-Python: >=3.9
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: numpy>=1.24
+Requires-Dist: scipy>=1.10
+Provides-Extra: dev
+Requires-Dist: pytest>=7.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0; extra == "dev"
+Dynamic: license-file
+
+# pyturboquant-cpu
+
+CPU implementation of **TurboQuant**, a data-oblivious vector quantization algorithm for compressing high-dimensional vectors with near-optimal distortion.
+
+Based on the paper: [TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate](https://arxiv.org/abs/2504.19874) (Zandieh et al., ICLR 2026).
+
+## Installation
+
+```bash
+pip install pyturboquant-cpu
+```
+
+For development:
+
+```bash
+git clone https://github.com/pyturboquant/pyturboquant-cpu.git
+cd pyturboquant-cpu
+pip install -e ".[dev]"
+```
+
+## Quick Start
+
+### MSE-Optimal Quantization
+
+Minimizes mean-squared reconstruction error:
+
+```python
+import numpy as np
+from pyturboquant_cpu import quantize_mse, dequantize_mse
+
+# Random vectors (e.g., KV cache embeddings)
+vectors = np.random.randn(100, 128)  # 100 vectors of dimension 128
+
+# Quantize at 3 bits per coordinate
+quantized = quantize_mse(vectors, bits=3, seed=42)
+
+# Reconstruct
+reconstructed = dequantize_mse(quantized)
+
+# Check reconstruction quality
+mse = np.mean(np.sum((vectors - reconstructed) ** 2, axis=1))
+print(f"MSE: {mse:.4f}")
+```
+
+### Inner-Product-Optimal Quantization
+
+Provides **unbiased** inner product estimates — essential for attention mechanisms and nearest-neighbor search:
+
+```python
+from pyturboquant_cpu import quantize_prod, dequantize_prod
+
+# Quantize at 4 bits total (3 bits MSE + 1 bit QJL correction)
+quantized = quantize_prod(vectors, bits=4, seed=42)
+reconstructed = dequantize_prod(quantized)
+
+# Inner products are unbiased: E[⟨y, x̃⟩] = ⟨y, x⟩
+query = np.random.randn(128)
+true_ip = vectors @ query
+approx_ip = reconstructed @ query
+print(f"Mean IP error: {np.mean(np.abs(true_ip - approx_ip)):.4f}")
+```
+
+## How It Works
+
+TurboQuant is a **data-oblivious** algorithm — it requires no training data or calibration:
+
+1. **Random Rotation**: Input vectors are multiplied by a random orthogonal matrix, transforming coordinates to follow a known Beta distribution
+2. **Lloyd-Max Scalar Quantization**: Each coordinate is independently quantized using a precomputed optimal codebook for the Beta distribution
+3. **QJL Residual Correction** (Prod mode only): A 1-bit Quantized Johnson-Lindenstrauss sketch of the residual removes inner-product bias
+
+### Theoretical Distortion Bounds
+
+For unit vectors on S^{d-1}:
+
+| Bits | MSE Distortion | Inner Product Distortion |
+|------|---------------|-------------------------|
+| 1    | ≈ 0.36        | ≈ 1.57/d                |
+| 2    | ≈ 0.117       | ≈ 0.56/d                |
+| 3    | ≈ 0.03        | ≈ 0.18/d                |
+| 4    | ≈ 0.009       | ≈ 0.047/d               |
+
+These are within a factor of ~2.7× of the information-theoretic lower bound.
+
+## API Reference
+
+### `quantize_mse(vectors, bits, dim=None, seed=None)`
+
+Quantize vectors using TurboQuant_MSE (MSE-optimal).
+
+- **vectors**: array of shape `(..., d)` — input vectors
+- **bits**: int in `[1, 8]` — bits per coordinate
+- **seed**: int or None — random seed for reproducibility
+- **Returns**: `QuantizedMSE` dataclass
+
+### `dequantize_mse(quantized)`
+
+Reconstruct vectors from MSE quantization result.
+
+- **quantized**: `QuantizedMSE` — output of `quantize_mse`
+- **Returns**: ndarray with same shape as original input
+
+### `quantize_prod(vectors, bits, dim=None, seed=None)`
+
+Quantize vectors using TurboQuant_Prod (unbiased inner products).
+
+- **vectors**: array of shape `(..., d)` — input vectors
+- **bits**: int in `[2, 8]` — total bits per coordinate
+- **seed**: int or None — random seed
+- **Returns**: `QuantizedProd` dataclass
+
+### `dequantize_prod(quantized)`
+
+Reconstruct vectors from Prod quantization result.
+
+- **quantized**: `QuantizedProd` — output of `quantize_prod`
+- **Returns**: ndarray with same shape as original input
+
+## GPU Version
+
+For GPU-accelerated quantization using PyTorch, see the companion package:
+
+```bash
+pip install pyturboquant-gpu
+```
+
+## Citation
+
+```bibtex
+@article{zandieh2025turboquant,
+  title={TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate},
+  author={Zandieh, Amir and Daliri, Majid and Hadian, Majid and Mirrokni, Vahab},
+  journal={arXiv preprint arXiv:2504.19874},
+  year={2025}
+}
+```
+
+## License
+
+Apache 2.0

pyturboquant_cpu-0.1.0/README.md

@@ -0,0 +1,139 @@
+# pyturboquant-cpu
+
+CPU implementation of **TurboQuant**, a data-oblivious vector quantization algorithm for compressing high-dimensional vectors with near-optimal distortion.
+
+Based on the paper: [TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate](https://arxiv.org/abs/2504.19874) (Zandieh et al., ICLR 2026).
+
+## Installation
+
+```bash
+pip install pyturboquant-cpu
+```
+
+For development:
+
+```bash
+git clone https://github.com/pyturboquant/pyturboquant-cpu.git
+cd pyturboquant-cpu
+pip install -e ".[dev]"
+```
+
+## Quick Start
+
+### MSE-Optimal Quantization
+
+Minimizes mean-squared reconstruction error:
+
+```python
+import numpy as np
+from pyturboquant_cpu import quantize_mse, dequantize_mse
+
+# Random vectors (e.g., KV cache embeddings)
+vectors = np.random.randn(100, 128)  # 100 vectors of dimension 128
+
+# Quantize at 3 bits per coordinate
+quantized = quantize_mse(vectors, bits=3, seed=42)
+
+# Reconstruct
+reconstructed = dequantize_mse(quantized)
+
+# Check reconstruction quality
+mse = np.mean(np.sum((vectors - reconstructed) ** 2, axis=1))
+print(f"MSE: {mse:.4f}")
+```
+
+### Inner-Product-Optimal Quantization
+
+Provides **unbiased** inner product estimates — essential for attention mechanisms and nearest-neighbor search:
+
+```python
+from pyturboquant_cpu import quantize_prod, dequantize_prod
+
+# Quantize at 4 bits total (3 bits MSE + 1 bit QJL correction)
+quantized = quantize_prod(vectors, bits=4, seed=42)
+reconstructed = dequantize_prod(quantized)
+
+# Inner products are unbiased: E[⟨y, x̃⟩] = ⟨y, x⟩
+query = np.random.randn(128)
+true_ip = vectors @ query
+approx_ip = reconstructed @ query
+print(f"Mean IP error: {np.mean(np.abs(true_ip - approx_ip)):.4f}")
+```
+
+## How It Works
+
+TurboQuant is a **data-oblivious** algorithm — it requires no training data or calibration:
+
+1. **Random Rotation**: Input vectors are multiplied by a random orthogonal matrix, transforming coordinates to follow a known Beta distribution
+2. **Lloyd-Max Scalar Quantization**: Each coordinate is independently quantized using a precomputed optimal codebook for the Beta distribution
+3. **QJL Residual Correction** (Prod mode only): A 1-bit Quantized Johnson-Lindenstrauss sketch of the residual removes inner-product bias
+
+### Theoretical Distortion Bounds
+
+For unit vectors on S^{d-1}:
+
+| Bits | MSE Distortion | Inner Product Distortion |
+|------|---------------|-------------------------|
+| 1    | ≈ 0.36        | ≈ 1.57/d                |
+| 2    | ≈ 0.117       | ≈ 0.56/d                |
+| 3    | ≈ 0.03        | ≈ 0.18/d                |
+| 4    | ≈ 0.009       | ≈ 0.047/d               |
+
+These are within a factor of ~2.7× of the information-theoretic lower bound.
+
+## API Reference
+
+### `quantize_mse(vectors, bits, dim=None, seed=None)`
+
+Quantize vectors using TurboQuant_MSE (MSE-optimal).
+
+- **vectors**: array of shape `(..., d)` — input vectors
+- **bits**: int in `[1, 8]` — bits per coordinate
+- **seed**: int or None — random seed for reproducibility
+- **Returns**: `QuantizedMSE` dataclass
+
+### `dequantize_mse(quantized)`
+
+Reconstruct vectors from MSE quantization result.
+
+- **quantized**: `QuantizedMSE` — output of `quantize_mse`
+- **Returns**: ndarray with same shape as original input
+
+### `quantize_prod(vectors, bits, dim=None, seed=None)`
+
+Quantize vectors using TurboQuant_Prod (unbiased inner products).
+
+- **vectors**: array of shape `(..., d)` — input vectors
+- **bits**: int in `[2, 8]` — total bits per coordinate
+- **seed**: int or None — random seed
+- **Returns**: `QuantizedProd` dataclass
+
+### `dequantize_prod(quantized)`
+
+Reconstruct vectors from Prod quantization result.
+
+- **quantized**: `QuantizedProd` — output of `quantize_prod`
+- **Returns**: ndarray with same shape as original input
+
+## GPU Version
+
+For GPU-accelerated quantization using PyTorch, see the companion package:
+
+```bash
+pip install pyturboquant-gpu
+```
+
+## Citation
+
+```bibtex
+@article{zandieh2025turboquant,
+  title={TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate},
+  author={Zandieh, Amir and Daliri, Majid and Hadian, Majid and Mirrokni, Vahab},
+  journal={arXiv preprint arXiv:2504.19874},
+  year={2025}
+}
+```
+
+## License
+
+Apache 2.0

pyturboquant_cpu-0.1.0/pyproject.toml

@@ -0,0 +1,57 @@
+[build-system]
+requires = ["setuptools>=68.0", "setuptools-scm>=8.0"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "pyturboquant-cpu"
+version = "0.1.0"
+description = "CPU implementation of TurboQuant data-oblivious vector quantization (arXiv:2504.19874)"
+readme = "README.md"
+license = "Apache-2.0"
+requires-python = ">=3.9"
+authors = [
+    {name = "pyturboquant contributors"},
+]
+keywords = [
+    "vector-quantization",
+    "kv-cache",
+    "llm",
+    "compression",
+    "turboquant",
+    "quantization",
+]
+classifiers = [
+    "Development Status :: 3 - Alpha",
+    "Intended Audience :: Developers",
+    "Intended Audience :: Science/Research",
+    "Programming Language :: Python :: 3",
+    "Programming Language :: Python :: 3.9",
+    "Programming Language :: Python :: 3.10",
+    "Programming Language :: Python :: 3.11",
+    "Programming Language :: Python :: 3.12",
+    "Topic :: Scientific/Engineering :: Artificial Intelligence",
+    "Topic :: Scientific/Engineering :: Mathematics",
+]
+dependencies = [
+    "numpy>=1.24",
+    "scipy>=1.10",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=7.0",
+    "pytest-cov>=4.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/pyturboquant/pyturboquant-cpu"
+Documentation = "https://github.com/pyturboquant/pyturboquant-cpu#readme"
+Repository = "https://github.com/pyturboquant/pyturboquant-cpu"
+Issues = "https://github.com/pyturboquant/pyturboquant-cpu/issues"
+
+[tool.setuptools.packages.find]
+where = ["src"]
+
+[tool.pytest.ini_options]
+testpaths = ["tests"]
+addopts = "-v"

pyturboquant_cpu-0.1.0/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

pyturboquant_cpu-0.1.0/src/pyturboquant_cpu/__init__.py

@@ -0,0 +1,36 @@
+"""
+pyturboquant-cpu: CPU implementation of TurboQuant vector quantization.
+
+TurboQuant is a data-oblivious vector quantization algorithm from
+"TurboQuant: Online Vector Quantization with Near-optimal Distortion Rate"
+(Zandieh et al., arXiv:2504.19874).
+
+Two quantization modes are provided:
+
+- **MSE-optimal** (``quantize_mse`` / ``dequantize_mse``):
+  Minimises mean-squared reconstruction error.
+- **Inner-product-optimal** (``quantize_prod`` / ``dequantize_prod``):
+  Gives an *unbiased* inner-product estimator by combining an MSE
+  quantizer with a 1-bit QJL residual correction.
+"""
+
+from pyturboquant_cpu.quantizer import (
+    QuantizedMSE,
+    QuantizedProd,
+    quantize_mse,
+    dequantize_mse,
+    quantize_prod,
+    dequantize_prod,
+)
+
+__version__ = "0.1.0"
+
+__all__ = [
+    "quantize_mse",
+    "dequantize_mse",
+    "quantize_prod",
+    "dequantize_prod",
+    "QuantizedMSE",
+    "QuantizedProd",
+    "__version__",
+]