# Kwker documentation

Kwker makes CPU work quicker - PyTorch models, LLM text generation, embeddings, DataFrames and sorting - from Python, Rust, C, C++ and 16 more languages.

Web page: https://kwker.io/docs/ - every Kwker documentation page for AI assistants: https://kwker.io/llms.txt

Kwker makes the work you already run on CPUs quicker: PyTorch models, text generation with LLMs, embeddings, image
models, DataFrame group-bys and sorts, and the sorting and top-k calls underneath all of them. Install one package,
change one line, and measure the difference on your own machine.

1. **Install.** `pip install kwker`, or the package for Rust, C, C++, JavaScript, Go, Java, C# and
   [12 more languages](https://kwker.io/docs/md/languages.md).
2. **Add one line.** `kwker.torch_ops.install()`, or [the line for your workload](https://kwker.io/docs/md/integrate.md): LLMs, embeddings,
   image models, DataFrames.
3. **Measure it.** `python -m kwker.bench` on your machine, then [compare your own program](https://kwker.io/docs/md/evaluate.md) with and
   without Kwker.

## What are you working on?

- [Accelerate PyTorch](https://kwker.io/docs/md/pytorch.md)
- [Accelerate Hugging Face](https://kwker.io/docs/md/hf.md)
- [Classify images](https://kwker.io/docs/md/vision.md)
- [Data and analytics](https://kwker.io/docs/md/data.md)
- [Quickstart: Kwker Core](https://kwker.io/docs/md/quickstart-core.md)
- [Evaluate on your machine](https://kwker.io/docs/md/evaluate.md)

> [!NOTE]
> This documentation describes the 0.1.0 release. Package names and download links take effect with the release.

## Try it

Press **Run** to run this example in your browser. You can edit it first.

```python
import numpy as np
import kwker

prices = np.array([19.99, 4.50, 120.00, 4.50, 35.25])
kwker.sort(prices)
print(prices)

scores = np.array([7, 42, 3, 99, 15])
values, positions = kwker.top_k(scores, 2, descending=True)
print(values, positions)
```

```text
[  4.5    4.5   19.99  35.25 120.  ]
[99 42] [3 1]
```

The [Playground](playground/index.html) has more examples in Python and JavaScript.

## Browse the documentation

- **Get started**
  - [Add Kwker to your project](https://kwker.io/docs/md/integrate.md)
  - [Evaluate on your machine](https://kwker.io/docs/md/evaluate.md)
  - [Quickstarts](https://kwker.io/docs/md/quickstart.md)
  - [Installation](https://kwker.io/docs/md/install.md)
- **Tutorials**
  - [Rank a leaderboard](https://kwker.io/docs/md/tutorial-leaderboard.md)
  - [Top-k recommendations](https://kwker.io/docs/md/tutorial-recommendations.md)
  - [Group-by on a table](https://kwker.io/docs/md/tutorial-groupby.md)
  - [All tutorials](https://kwker.io/docs/md/tutorials.md)
- **Learn**
  - [Core concepts](https://kwker.io/docs/md/concepts.md)
  - [All operations](https://kwker.io/docs/md/operations.md)
  - [Runtime controls](https://kwker.io/docs/md/cpu-runtime.md)
  - [Release notes](https://kwker.io/docs/md/release-notes.md)
- **How-to guides**
  - [Sorting](https://kwker.io/docs/md/sorting.md)
  - [Top-k and selection](https://kwker.io/docs/md/top-k.md)
  - [Order and ranking](https://kwker.io/docs/md/ordering.md)
  - [Keys with values](https://kwker.io/docs/md/key-value.md)
  - [All how-to guides](https://kwker.io/docs/md/guides.md)
- **Build with Kwker**
  - [NumPy drop-in](https://kwker.io/docs/md/numpy.md)
  - [DataFrames, Arrow and DuckDB](https://kwker.io/docs/md/dataframes.md)
  - [Accelerate PyTorch](https://kwker.io/docs/md/pytorch.md)
  - [Large data](https://kwker.io/docs/md/large-data.md)
  - [All languages](https://kwker.io/docs/md/languages.md)
- **Reference**
  - [Python API](https://kwker.io/docs/md/reference-python.md)
  - [C API](https://kwker.io/docs/md/reference-c.md)
  - [C++ API](https://kwker.io/docs/md/reference-cpp.md)
  - [All API references](https://kwker.io/docs/md/reference.md)
- **Help**
  - [Troubleshooting](https://kwker.io/docs/md/troubleshooting.md)
  - [Known limitations](https://kwker.io/docs/md/limitations.md)
  - [Compatibility](https://kwker.io/docs/md/compatibility.md)

Every function is listed in the API reference for [Python](https://kwker.io/docs/md/reference-python.md), [C](https://kwker.io/docs/md/reference-c.md),
[C++](https://kwker.io/docs/md/reference-cpp.md), [Go](https://kwker.io/docs/md/reference-go.md), [JavaScript / TypeScript](https://kwker.io/docs/md/reference-js.md), [Java](https://kwker.io/docs/md/reference-java.md),
[C#](https://kwker.io/docs/md/reference-csharp.md), [Ruby](https://kwker.io/docs/md/reference-ruby.md), [R](https://kwker.io/docs/md/reference-r.md), [PHP](https://kwker.io/docs/md/reference-php.md) and [Perl](https://kwker.io/docs/md/reference-perl.md). Rust users can run `cargo doc -p kwker --open`.
A function named in these pages links to its entry there. Point at the name to see what it does and its arguments.

## What runs where

| Platform | Engines | Packages |
| --- | --- | --- |
| Linux x86-64 | AVX-512, AVX2, portable | Python wheel (with PyTorch extensions), C / C++ archive, .deb, .rpm, Rust crate |
| Linux ARM64 | SVE (64-bit keys), NEON, portable | Python wheel, C / C++ archive, .deb, .rpm, Rust crate |
| Windows x64 | AVX-512, AVX2, portable | Python wheel, C / C++ zip, Rust crate (clang++) |
| macOS ARM64 (Apple silicon) | NEON, portable | Python wheel, C / C++ archive, Rust crate |
| macOS x86-64 | AVX2, portable | Rust crate and source builds only |

The PyTorch extensions (drop-in kernels, CPU backend, KwkCNN / KwkEncoder / KwkDecoder) are built for Linux x86-64.

## Check your installation

```python
import kwker
print(kwker.version(), kwker.isa())     # e.g. 0.1.0 avx512
```

`python -m kwker doctor` prints the full picture: CPU, engines, operating system, threads and framework versions,
with a warning for anything that limits speed or compatibility.