What is Quadrants?

Quadrants is a high-performance multi-platform compiler for physics simulation being continuously developed by Genesis AI.

It is designed for large-scale physics simulation and robotics workloads. It compiles Python code into highly optimized parallel kernels that run on:

NVIDIA GPUs (CUDA)
Vulkan-compatible GPUs (SPIR-V)
Apple Metal GPUs
AMD GPUs (ROCm HIP)
x86 and ARM64 CPUs

The origin

The quadrants project was originally forked from Taichi in June 2025. As the original Taichi is no longer being maintained and the codebase evolved into a fully independent compiler with its own direction and long-term roadmap, we decided to give it a name that reflects both its roots and its new identity. The name Quadrants is inspired by the Chinese saying:

太极生两仪，两仪生四象

The Supreme Polarity (Taichi) gives rise to the Two Modes (Yin & Yang), which in turn give rise to the Four Forms (Quadrants).

Quadrants captures the idea of progression originated from taichi — built on the same foundation, evolving in its own direction while acknowledging its roots. This project is now fully independent and does not aim to maintain backward compatibility with upstream Taichi.

How Quadrants differs from upstream Taichi

While the repository still resembles upstream in structure, major changes include:

Platform support

LLVM 22, ARM (aarch64) support

CI

Kernel-level code coverage — device-side branch coverage in standard coverage.py format, integrated with pytest-cov
AI-driven checks for line wrapping, deleted comments, test coverage, and feature factorization

Structural improvements

dataclasses.dataclass structs — work with ndarrays and fields, nestable, passable to qd.func, zero kernel-runtime overhead
qd.Tensor — unified API over fields and ndarrays with per-tensor layout control, pickle support, and a backend= switch
BufferView — safe sub-range ndarray access with bounds checking in debug mode

Removed components

To focus the compiler and reduce maintenance burden, we removed: GUI/GGUI, C-API, AOT, DX11/DX12, iOS/Android, OpenGL/GLES, argpack, CLI.

Performance

Reduced launch latency — ndarray CPU performance improved 4.5×; ndarray GPU performance went from 11× slower than fields to ~30% slower (5090 GPU, Genesis benchmark)
Fastcache — opt-in source-level cache (@qd.kernel(fastcache=True)) that bypasses front-end AST parsing; reduces warm-cache kernel load from 7.2 s → 0.3 s on Genesis benchmarks
GPU Graphs — @qd.kernel(graph=True) captures kernel sequences into a graph; qd.graph_do_while runs GPU-side iteration loops (hardware conditional nodes on CUDA SM 9.0+)
perf_dispatch — auto-benchmarks multiple kernel implementations and selects the fastest at runtime
Zero-copy interop — to_torch(copy=False) / to_numpy(copy=False) via DLPack on CUDA, CPU, AMDGPU, and Metal; direct torch tensor pass-through into kernels

SIMT primitives

Tile16x16 / Tile32x32 — register-resident 16×16 and 32×32 matrix tiles with Cholesky, triangular solve, and rank-1 updates; 5× faster than shared-memory baselines on blocked linear algebra
Subgroup ops — cross-platform shuffle, shuffle_down, reduce_add, reduce_all_add across CUDA, AMDGPU, Metal and Vulkan

Autodiff

Autodiff with dynamic loops — computes the gradient of any kernel transparently using reverse-mode differentiation and runtime-based memory allocation
Forward-mode AD, custom gradients (@qd.ad.grad_replaced), qd.ad.Tape

Debugging & development

Python backend — qd.init(qd.python) interprets kernels as plain Python so they can be stepped through in a standard Python debugger

Installation

Prerequisites

Python 3.10-3.13
Mac OS 14, 15, Windows, or Ubuntu 22.04-24.04 or compatible
ROCm 5.2 or newer for AMD GPU support

Procedure

pip install quadrants

(For how to build from source, see our CI build scripts, e.g. linux build scripts )

Documentation

Something is broken!

Create an issue

Acknowledgements

Quadrants stands on the shoulders of the original Taichi project, built with care and vision by many contributors over the years. For the full list of contributors and credits, see the original Taichi repository.

We are grateful for that foundation.

Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distributions

No source distribution files available for this release.See tutorial on generating distribution archives.

Built Distributions

If you're not sure about the file name format, learn more about wheel file names.

The dropdown lists show the available interpreters, ABIs, and platforms. Enable javascript to be able to filter the list of wheel files.

quadrants-1.1.2-cp313-cp313-win_amd64.whl (31.0 MB view details)

Uploaded Jul 15, 2026 CPython 3.13Windows x86-64

quadrants-1.1.2-cp313-cp313-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (40.9 MB view details)

Uploaded Jul 15, 2026 CPython 3.13manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

quadrants-1.1.2-cp313-cp313-manylinux_2_27_aarch64.manylinux_2_34_aarch64.whl (38.3 MB view details)

Uploaded Jul 15, 2026 CPython 3.13manylinux: glibc 2.27+ ARM64manylinux: glibc 2.34+ ARM64

quadrants-1.1.2-cp313-cp313-macosx_11_0_arm64.whl (26.7 MB view details)

Uploaded Jul 15, 2026 CPython 3.13macOS 11.0+ ARM64

quadrants-1.1.2-cp312-cp312-win_amd64.whl (31.0 MB view details)

Uploaded Jul 15, 2026 CPython 3.12Windows x86-64

quadrants-1.1.2-cp312-cp312-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (40.9 MB view details)

Uploaded Jul 15, 2026 CPython 3.12manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

quadrants-1.1.2-cp312-cp312-manylinux_2_27_aarch64.manylinux_2_34_aarch64.whl (38.3 MB view details)

Uploaded Jul 15, 2026 CPython 3.12manylinux: glibc 2.27+ ARM64manylinux: glibc 2.34+ ARM64

quadrants-1.1.2-cp312-cp312-macosx_11_0_arm64.whl (26.7 MB view details)

Uploaded Jul 15, 2026 CPython 3.12macOS 11.0+ ARM64

quadrants-1.1.2-cp311-cp311-win_amd64.whl (31.0 MB view details)

Uploaded Jul 15, 2026 CPython 3.11Windows x86-64

quadrants-1.1.2-cp311-cp311-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (40.9 MB view details)

Uploaded Jul 15, 2026 CPython 3.11manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

quadrants-1.1.2-cp311-cp311-manylinux_2_27_aarch64.manylinux_2_34_aarch64.whl (38.3 MB view details)

Uploaded Jul 15, 2026 CPython 3.11manylinux: glibc 2.27+ ARM64manylinux: glibc 2.34+ ARM64

quadrants-1.1.2-cp311-cp311-macosx_11_0_arm64.whl (26.7 MB view details)

Uploaded Jul 15, 2026 CPython 3.11macOS 11.0+ ARM64

quadrants-1.1.2-cp310-cp310-win_amd64.whl (30.9 MB view details)

Uploaded Jul 15, 2026 CPython 3.10Windows x86-64

quadrants-1.1.2-cp310-cp310-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl (40.9 MB view details)

Uploaded Jul 15, 2026 CPython 3.10manylinux: glibc 2.27+ x86-64manylinux: glibc 2.28+ x86-64

quadrants-1.1.2-cp310-cp310-manylinux_2_27_aarch64.manylinux_2_34_aarch64.whl (38.3 MB view details)

Uploaded Jul 15, 2026 CPython 3.10manylinux: glibc 2.27+ ARM64manylinux: glibc 2.34+ ARM64

quadrants-1.1.2-cp310-cp310-macosx_11_0_arm64.whl (26.7 MB view details)

Uploaded Jul 15, 2026 CPython 3.10macOS 11.0+ ARM64

File details

Details for the file quadrants-1.1.2-cp313-cp313-win_amd64.whl.

File metadata

Download URL: quadrants-1.1.2-cp313-cp313-win_amd64.whl
Upload date: Jul 15, 2026
Size: 31.0 MB
Tags: CPython 3.13, Windows x86-64
Uploaded using Trusted Publishing? Yes
Uploaded via: twine/6.2.0 CPython/3.10.20

File hashes

Hashes for quadrants-1.1.2-cp313-cp313-win_amd64.whl
Algorithm	Hash digest
SHA256	`7778bf961a5ec7d75cadf983f5d2b7257f8f688a6fad5f73c6128317c6838050`
MD5	`ef22391a5a48480fb69c2d4e8fc6b5cf`
BLAKE2b-256	`020b0c634b4e05cb50196fe4ae765a34065a3c7451e52eb01f32ee132e8fe963`

Algorithm	Hash digest
SHA256	`c05c45e9cecc24977b5483ca7626cf3c23f17513500914a0c352fdbe541656a4`
MD5	`a23ac1fbf473707e3cf85d0306f68d35`
BLAKE2b-256	`e71c949511c21e8975023de4ef7c0f49712864fb3d1eca1d711147d5b420de4a`

Algorithm	Hash digest
SHA256	`83d819dfaab257479f6cedeb53e387df7c406f1dd6f6164cbb564339b02be51e`
MD5	`e13febb6ad60f528066abe404ad2b0a0`
BLAKE2b-256	`b340209f9be1a50a9f55e89add334373077214fe61f5d514e33a241d20409ab3`

Algorithm	Hash digest
SHA256	`ddfefb5c111a9a56752cbdd7da4ac7fb1412af25dc7b2205f050ea461820e267`
MD5	`9388a24c392232b05c7256e886eebadd`
BLAKE2b-256	`1690ed8858dc47fec6d9358ecbb75dc52a9d2e8c64b56ad366401e31571c885b`

Algorithm	Hash digest
SHA256	`19ffc446fec14a83f55711092661dfab44225f50583041343adf734400e6245a`
MD5	`fdf67444d89081cd3e80afce83bae67e`
BLAKE2b-256	`a0a351ced7d3f6332f10145625916a691abc0cef99e2c704c39eadf595c20359`

Algorithm	Hash digest
SHA256	`c336b3d05e45619b4ebedbcfe274fb00a32227ccce0909ac8d8214cc2a19ea41`
MD5	`c16a76b3365bd5b77e3fc70afbab2a37`
BLAKE2b-256	`8e1b9e35470d0a385e530cd87dc36c96e560d0d03659811d1707e2cdc63dd0bd`

Algorithm	Hash digest
SHA256	`252c1a637c798636ca4f11616d43a8024939d374257b2e533e14ea70bcf21684`
MD5	`107c892f2ef4060844fd18ccaa7b19ee`
BLAKE2b-256	`0d1d7afe186178886e8bcce8e2dfe9a0eb5864d4bc183b19dd152b930bb24c49`

Algorithm	Hash digest
SHA256	`26b79a4c142c709a9d016aab33eea615f1d40b72d1129fb77d958c77965fc896`
MD5	`adcc605282f9d3b9eb2e07b9c257c116`
BLAKE2b-256	`475e82ca4e1ddc9f9be514474ae6888836c02d2ec39b10f981e11770c939c46b`

Algorithm	Hash digest
SHA256	`469b1af7fc679ff3843b9561e45785ba42012f57d38caa1dbff5567d98d402cf`
MD5	`400003eb46c8c909bdcf6a0b2d623408`
BLAKE2b-256	`37814d6fa8efdc084cbf1784fbd24e9894fa0422e8093c42a5a0e1447206e928`

Algorithm	Hash digest
SHA256	`36c1d8b6e8df75b733fb35c6cc852bcac4451d995913da091400acdcf5ee237f`
MD5	`f88c2f3bdfb0a145d6f7df162fdd8336`
BLAKE2b-256	`b3951dda09e36b7d6ba344dab862a489467bef6f6bf8a18a178859cf7afcce5d`

Algorithm	Hash digest
SHA256	`2a4f3b0935d167692e15eb6e06827c53b68a7f6f66e7aeade5df32abe71cb5e6`
MD5	`2e7d363c3e504dd7b54761c031b3e89e`
BLAKE2b-256	`f0b7151d944fa0c4d9c8ad03ae5527d34e8f789f7e16e3cf0345c6646c1cae64`

Algorithm	Hash digest
SHA256	`9120aee01d84f441121b9ee6300107009254a44d0222791543fdb6ebf6444e4c`
MD5	`37a34f978be92ee486a3ac35cec55a3a`
BLAKE2b-256	`ce09f82e25c52691fd7a1f3e3ffae3d0e33c164080297a560306a852c5b10f71`

Algorithm	Hash digest
SHA256	`5cdacbb913e8169ac2aefcd1122c559d701cc8ac3e23a949cc4f2a8b78de0b30`
MD5	`bf4e75682ffa2ebe913d8c774bb1574c`
BLAKE2b-256	`0252b822f431eff4a04e556d9ef95cbada5cd3414022b3c1cf56ebc0f6aa0d43`

Algorithm	Hash digest
SHA256	`906cafcbbe77b33ca8716726617977b5a0accafe85776faabcb87b4ef579390a`
MD5	`a9ce599f491e5d9b6869e2810d6e7485`
BLAKE2b-256	`d1cd0d9912c3d923427f0528adfa34dcfd8e0d6f0b9c7625f4bb3a558e93d71c`

Algorithm	Hash digest
SHA256	`78133dacf31a26249f2fa69ad14303ee978832ec05d3746a3bd1e2db3507beac`
MD5	`af77b94b2da47c8f34178357e0efddfd`
BLAKE2b-256	`50ed5a7b23012bf39b943b838d4ed448ea4dcf505a577eb0cf2eb70eb6181edc`

Algorithm	Hash digest
SHA256	`d9d0e75f096e4f01dc1a865783515d725c418d506a394704006405e6e1720c83`
MD5	`41d4355fc838275cdd50fd70884c4de7`
BLAKE2b-256	`e8e6d6bb6f4c99fcbd8398f92c9e0f0c321bc516b3925308753190516e74c8fb`

quadrants 1.1.2

What is Quadrants?

The origin

How Quadrants differs from upstream Taichi

Platform support

CI

Structural improvements

Removed components

Performance

SIMT primitives

Autodiff

Debugging & development

Installation

Prerequisites

Procedure

Documentation

Something is broken!

Acknowledgements

Project links

Key dates

Owner

1 maintainer

Credits

GitHub Statistics

License expression

Requires

Tags

Classifiers

Download files

Source Distributions

Built Distributions

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

File details

File metadata

File hashes

Release history Release notifications | RSS feed