{"id":13564064,"url":"https://github.com/NVIDIA/warp","last_synced_at":"2025-04-03T21:30:26.200Z","repository":{"id":37681583,"uuid":"471527576","full_name":"NVIDIA/warp","owner":"NVIDIA","description":"A Python framework for high performance GPU simulation and graphics","archived":false,"fork":false,"pushed_at":"2025-04-01T18:32:54.000Z","size":49310,"stargazers_count":4837,"open_issues_count":153,"forks_count":284,"subscribers_count":46,"default_branch":"main","last_synced_at":"2025-04-02T15:07:40.583Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"https://nvidia.github.io/warp/","language":"Python","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"apache-2.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/NVIDIA.png","metadata":{"files":{"readme":"README.md","changelog":"CHANGELOG.md","contributing":"CONTRIBUTING.md","funding":null,"license":"LICENSE.md","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":".gitlab/CODEOWNERS","security":"SECURITY.md","support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null}},"created_at":"2022-03-18T21:56:23.000Z","updated_at":"2025-04-02T14:33:11.000Z","dependencies_parsed_at":"2024-03-08T02:44:01.241Z","dependency_job_id":"0ad2e00d-35f8-4b6b-8a01-a663bd0de5b4","html_url":"https://github.com/NVIDIA/warp","commit_stats":{"total_commits":2788,"total_committers":48,"mean_commits":"58.083333333333336","dds":0.7109038737446198,"last_synced_commit":"d706d158d051a40f661c11d23a81b1cc3e15e403"},"previous_names":[],"tags_count":48,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA%2Fwarp","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA%2Fwarp/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA%2Fwarp/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/NVIDIA%2Fwarp/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/NVIDIA","download_url":"https://codeload.github.com/NVIDIA/warp/tar.gz/refs/heads/main","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247082747,"owners_count":20880711,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2024-08-01T13:01:26.206Z","updated_at":"2025-04-03T21:30:21.181Z","avatar_url":"https://github.com/NVIDIA.png","language":"Python","readme":"[![PyPI version](https://badge.fury.io/py/warp-lang.svg)](https://badge.fury.io/py/warp-lang)\n![GitHub commit activity](https://img.shields.io/github/commit-activity/m/NVIDIA/warp?link=https%3A%2F%2Fgithub.com%2FNVIDIA%2Fwarp%2Fcommits%2Fmain)\n[![Downloads](https://static.pepy.tech/badge/warp-lang/month)](https://pepy.tech/project/warp-lang)\n[![codecov](https://codecov.io/github/NVIDIA/warp/graph/badge.svg?token=7O1KSM79FG)](https://codecov.io/github/NVIDIA/warp)\n![GitHub - CI](https://github.com/NVIDIA/warp/actions/workflows/ci.yml/badge.svg)\n[![Discord](https://img.shields.io/badge/Discord-%235865F2.svg?logo=discord\u0026logoColor=white)](https://discord.com/invite/nvidiaomniverse)\n\n# NVIDIA Warp\n\nWarp is a Python framework for writing high-performance simulation and graphics code. Warp takes\nregular Python functions and JIT compiles them to efficient kernel code that can run on the CPU or GPU.\n\nWarp is designed for [spatial computing](https://en.wikipedia.org/wiki/Spatial_computing)\nand comes with a rich set of primitives that make it easy to write\nprograms for physics simulation, perception, robotics, and geometry processing. In addition, Warp kernels\nare differentiable and can be used as part of machine-learning pipelines with frameworks such as PyTorch and JAX.\n\nPlease refer to the project [Documentation](https://nvidia.github.io/warp/) for API and language reference and [CHANGELOG.md](./CHANGELOG.md) for release history.\n\n\u003cdiv align=\"center\"\u003e\n    \u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/header.jpg\"\u003e\n    \u003cp\u003e\u003ci\u003eA selection of physical simulations computed with Warp\u003c/i\u003e\u003c/p\u003e\n\u003c/div\u003e\n\n## Installing\n\nPython version 3.9 or newer is recommended. Warp can run on x86-64 and ARMv8 CPUs on Windows, Linux, and macOS.\nGPU support requires a CUDA-capable NVIDIA GPU and driver (minimum GeForce GTX 9xx).\n\nThe easiest way to install Warp is from [PyPI](https://pypi.org/project/warp-lang/):\n\n```text\npip install warp-lang\n```\n\nYou can also use `pip install warp-lang[extras]` to install additional dependencies for running examples and USD-related features.\n\nThe binaries hosted on PyPI are currently built with the CUDA 12 runtime and therefore\nrequire a minimum version of the CUDA driver of 525.60.13 (Linux x86-64) or 528.33 (Windows x86-64).\n\nIf you require GPU support on a system with an older CUDA driver, you can build Warp from source or\ninstall wheels built with the CUDA 11.8 runtime from the [GitHub Releases](https://github.com/NVIDIA/warp/releases) page.\nCopy the URL of the appropriate wheel file (`warp-lang-{ver}+cu12-py3-none-{platform}.whl`) and pass it to\nthe `pip install` command, e.g.\n\n| Platform        | Install Command                                                                                                               |\n| --------------- | ----------------------------------------------------------------------------------------------------------------------------- |\n| Linux aarch64   | `pip install https://github.com/NVIDIA/warp/releases/download/v1.3.1/warp_lang-1.3.1+cu11-py3-none-manylinux2014_aarch64.whl` |\n| Linux x86-64    | `pip install https://github.com/NVIDIA/warp/releases/download/v1.3.1/warp_lang-1.3.1+cu11-py3-none-manylinux2014_x86_64.whl`  |\n| Windows x86-64  | `pip install https://github.com/NVIDIA/warp/releases/download/v1.3.1/warp_lang-1.3.1+cu11-py3-none-win_amd64.whl`             |\n\nThe `--force-reinstall` option may need to be used to overwrite a previous installation.\n\n### CUDA Requirements\n\n* Warp packages built with CUDA Toolkit 11.x require NVIDIA driver 470 or newer.\n* Warp packages built with CUDA Toolkit 12.x require NVIDIA driver 525 or newer.\n\nThis applies to pre-built packages distributed on PyPI and GitHub and also when building Warp from source.\n\nNote that building Warp with the `--quick` flag changes the driver requirements.  The quick build skips CUDA backward compatibility, so the minimum required driver is determined by the CUDA Toolkit version.  Refer to the [latest CUDA Toolkit release notes](https://docs.nvidia.com/cuda/cuda-toolkit-release-notes/index.html) to find the minimum required driver for different CUDA Toolkit versions (e.g., [this table from CUDA Toolkit 12.5](https://docs.nvidia.com/cuda/archive/12.5.0/cuda-toolkit-release-notes/index.html#id3)).\n\nWarp checks the installed driver during initialization and will report a warning if the driver is not suitable, e.g.:\n\n```text\nWarp UserWarning:\n   Insufficient CUDA driver version.\n   The minimum required CUDA driver version is 12.0, but the installed CUDA driver version is 11.8.\n   Visit https://github.com/NVIDIA/warp/blob/main/README.md#installing for guidance.\n```\n\nThis will make CUDA devices unavailable, but the CPU can still be used.\n\nTo remedy the situation there are a few options:\n\n* Update the driver.\n* Install a compatible pre-built Warp package.\n* Build Warp from source using a CUDA Toolkit that's compatible with the installed driver.\n\n## Getting Started\n\nAn example first program that computes the lengths of random 3D vectors is given below:\n\n```python\nimport warp as wp\nimport numpy as np\n\nnum_points = 1024\n\n@wp.kernel\ndef length(points: wp.array(dtype=wp.vec3),\n           lengths: wp.array(dtype=float)):\n\n    # thread index\n    tid = wp.tid()\n    \n    # compute distance of each point from origin\n    lengths[tid] = wp.length(points[tid])\n\n\n# allocate an array of 3d points\npoints = wp.array(np.random.rand(num_points, 3), dtype=wp.vec3)\nlengths = wp.zeros(num_points, dtype=float)\n\n# launch kernel\nwp.launch(kernel=length,\n          dim=len(points),\n          inputs=[points, lengths])\n\nprint(lengths)\n```\n\n## Running Examples\n\nThe [warp/examples](./warp/examples/) directory contains a number of scripts categorized under subdirectories\nthat show how to implement various simulation methods using the Warp API.\nMost examples will generate USD files containing time-sampled animations in the current working directory.\nBefore running examples, users should ensure that the ``usd-core``, ``matplotlib``, and ``pyglet`` packages are installed using:\n\n```text\npip install warp-lang[extras]\n```\n\nThese dependencies can also be manually installed using:\n\n```text\npip install usd-core matplotlib pyglet\n```\n\nExamples can be run from the command-line as follows:\n\n```text\npython -m warp.examples.\u003cexample_subdir\u003e.\u003cexample\u003e\n```\n\nTo browse the example source code, you can open the directory where the files are located like this:\n\n```text\npython -m warp.examples.browse\n```\n\nMost examples can be run on either the CPU or a CUDA-capable device, but a handful require a CUDA-capable device. These are marked at the top of the example script.\n\nUSD files can be viewed or rendered inside [NVIDIA Omniverse](https://developer.nvidia.com/omniverse), Pixar's UsdView, and Blender. Note that Preview in macOS is not recommended as it has limited support for time-sampled animations.\n\nBuilt-in unit tests can be run from the command-line as follows:\n\n```text\npython -m warp.tests\n```\n\n### warp/examples/core\n\n\u003ctable\u003e\n    \u003ctbody\u003e\n        \u003ctr\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/core/example_dem.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/core_dem.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/core/example_fluid.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/core_fluid.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/core/example_graph_capture.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/core_graph_capture.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/core/example_marching_cubes.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/core_marching_cubes.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd align=\"center\"\u003edem\u003c/td\u003e\n            \u003ctd align=\"center\"\u003efluid\u003c/td\u003e\n            \u003ctd align=\"center\"\u003egraph capture\u003c/td\u003e\n            \u003ctd align=\"center\"\u003emarching cubes\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/core/example_mesh.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/core_mesh.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/core/example_nvdb.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/core_nvdb.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/core/example_raycast.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/core_raycast.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/core/example_raymarch.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/core_raymarch.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd align=\"center\"\u003emesh\u003c/td\u003e\n            \u003ctd align=\"center\"\u003envdb\u003c/td\u003e\n            \u003ctd align=\"center\"\u003eraycast\u003c/td\u003e\n            \u003ctd align=\"center\"\u003eraymarch\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/core/example_sph.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/core_sph.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/core/example_torch.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/core_torch.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/core/example_wave.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/core_wave.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd align=\"center\"\u003esph\u003c/td\u003e\n            \u003ctd align=\"center\"\u003etorch\u003c/td\u003e\n            \u003ctd align=\"center\"\u003ewave\u003c/td\u003e\n            \u003ctd align=\"center\"\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n    \u003c/tbody\u003e\n\u003c/table\u003e\n\n### warp/examples/fem\n\n\u003ctable\u003e\n    \u003ctbody\u003e\n        \u003ctr\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/fem/example_diffusion_3d.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/fem_diffusion_3d.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/fem/example_mixed_elasticity.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/fem_mixed_elasticity.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/fem/example_apic_fluid.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/fem_apic_fluid.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/fem/example_streamlines.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/fem_streamlines.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd align=\"center\"\u003ediffusion 3d\u003c/td\u003e\n            \u003ctd align=\"center\"\u003emixed elasticity\u003c/td\u003e\n            \u003ctd align=\"center\"\u003eapic fluid\u003c/td\u003e\n            \u003ctd align=\"center\"\u003estreamlines\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/fem/example_convection_diffusion.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/fem_convection_diffusion.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/fem/example_navier_stokes.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/fem_navier_stokes.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/fem/example_burgers.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/fem_burgers.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/fem/example_magnetostatics.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/fem_magnetostatics.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd align=\"center\"\u003econvection diffusion\u003c/td\u003e\n            \u003ctd align=\"center\"\u003enavier stokes\u003c/td\u003e\n            \u003ctd align=\"center\"\u003eburgers\u003c/td\u003e\n            \u003ctd align=\"center\"\u003emagnetostatics\u003c/td\u003e\n        \u003c/tr\u003e\n    \u003c/tbody\u003e\n\u003c/table\u003e\n\n### warp/examples/optim\n\n\u003ctable\u003e\n    \u003ctbody\u003e\n        \u003ctr\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/optim/example_bounce.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/optim_bounce.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/optim/example_cloth_throw.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/optim_cloth_throw.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/optim/example_diffray.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/optim_diffray.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/optim/example_drone.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/optim_drone.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd align=\"center\"\u003ebounce\u003c/td\u003e\n            \u003ctd align=\"center\"\u003ecloth throw\u003c/td\u003e\n            \u003ctd align=\"center\"\u003ediffray\u003c/td\u003e\n            \u003ctd align=\"center\"\u003edrone\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/optim/example_inverse_kinematics.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/optim_inverse_kinematics.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/optim/example_spring_cage.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/optim_spring_cage.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/optim/example_trajectory.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/optim_trajectory.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/optim/example_walker.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/optim_walker.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd align=\"center\"\u003einverse kinematics\u003c/td\u003e\n            \u003ctd align=\"center\"\u003espring cage\u003c/td\u003e\n            \u003ctd align=\"center\"\u003etrajectory\u003c/td\u003e\n            \u003ctd align=\"center\"\u003ewalker\u003c/td\u003e\n        \u003c/tr\u003e\n    \u003c/tbody\u003e\n\u003c/table\u003e\n\n### warp/examples/sim\n\n\u003ctable\u003e\n    \u003ctbody\u003e\n        \u003ctr\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/sim/example_cartpole.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/sim_cartpole.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/sim/example_cloth.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/sim_cloth.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/sim/example_granular.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/sim_granular.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/sim/example_granular_collision_sdf.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/sim_granular_collision_sdf.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd align=\"center\"\u003ecartpole\u003c/td\u003e\n            \u003ctd align=\"center\"\u003ecloth\u003c/td\u003e\n            \u003ctd align=\"center\"\u003egranular\u003c/td\u003e\n            \u003ctd align=\"center\"\u003egranular collision sdf\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/sim/example_jacobian_ik.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/sim_jacobian_ik.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/sim/example_quadruped.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/sim_quadruped.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/sim/example_rigid_chain.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/sim_rigid_chain.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/sim/example_rigid_contact.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/sim_rigid_contact.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd align=\"center\"\u003ejacobian ik\u003c/td\u003e\n            \u003ctd align=\"center\"\u003equadruped\u003c/td\u003e\n            \u003ctd align=\"center\"\u003erigid chain\u003c/td\u003e\n            \u003ctd align=\"center\"\u003erigid contact\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/sim/example_rigid_force.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/sim_rigid_force.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/sim/example_rigid_gyroscopic.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/sim_rigid_gyroscopic.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/sim/example_rigid_soft_contact.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/sim_rigid_soft_contact.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n            \u003ctd\u003e\u003ca href=\"https://github.com/NVIDIA/warp/tree/main/warp/examples/sim/example_soft_body.py\"\u003e\u003cimg src=\"https://github.com/NVIDIA/warp/raw/main/docs/img/examples/sim_soft_body.png\"\u003e\u003c/a\u003e\u003c/td\u003e\n        \u003c/tr\u003e\n        \u003ctr\u003e\n            \u003ctd align=\"center\"\u003erigid force\u003c/td\u003e\n            \u003ctd align=\"center\"\u003erigid gyroscopic\u003c/td\u003e\n            \u003ctd align=\"center\"\u003erigid soft contact\u003c/td\u003e\n            \u003ctd align=\"center\"\u003esoft body\u003c/td\u003e\n        \u003c/tr\u003e\n    \u003c/tbody\u003e\n\u003c/table\u003e\n\n## Building\n\nFor developers who want to build the library themselves, the following tools are required:\n\n* Microsoft Visual Studio 2019 upwards (Windows)\n* GCC 9.4 upwards (Linux)\n* CUDA Toolkit 11.5 or higher\n* [Git LFS](https://git-lfs.github.com/) installed\n\nAfter cloning the repository, users should run:\n\n```text\npython build_lib.py\n```\n\nUpon success, the script will output platform-specific binary files in `warp/bin/`.\nThe build script will look for the CUDA Toolkit in its default installation path.\nThis path can be overridden by setting the `CUDA_PATH` environment variable. Alternatively,\nthe path to the CUDA Toolkit can be passed to the build command as\n`--cuda_path=\"...\"`. After building, the Warp package should be installed using:\n\n```text\npip install -e .\n```\n\nThis ensures that subsequent modifications to the library will be reflected in the Python package.\n\n## Learn More\n\nPlease see the following resources for additional background on Warp:\n\n* [Product Page](https://developer.nvidia.com/warp-python)\n* [GTC 2022 Presentation](https://www.nvidia.com/en-us/on-demand/session/gtcspring22-s41599)\n* [GTC 2021 Presentation](https://www.nvidia.com/en-us/on-demand/session/gtcspring21-s31838)\n* [SIGGRAPH Asia 2021 Differentiable Simulation Course](https://dl.acm.org/doi/abs/10.1145/3476117.3483433)\n* [GTC 2024 Presentation](https://www.nvidia.com/en-us/on-demand/session/gtc24-s63345/)\n\nThe underlying technology in Warp has been used in a number of research projects at NVIDIA including the following publications:\n\n* Accelerated Policy Learning with Parallel Differentiable Simulation - Xu, J., Makoviychuk, V., Narang, Y., Ramos, F., Matusik, W., Garg, A., \u0026 Macklin, M. [(2022)](https://short-horizon-actor-critic.github.io)\n* DiSECt: Differentiable Simulator for Robotic Cutting - Heiden, E., Macklin, M., Narang, Y., Fox, D., Garg, A., \u0026 Ramos, F [(2021)](https://github.com/NVlabs/DiSECt)\n* gradSim: Differentiable Simulation for System Identification and Visuomotor Control - Murthy, J. Krishna, Miles Macklin, Florian Golemo, Vikram Voleti, Linda Petrini, Martin Weiss, Breandan Considine et al. [(2021)](https://gradsim.github.io)\n\n## Frequently Asked Questions\n\nSee the [FAQ](https://nvidia.github.io/warp/faq.html) in the Warp documentation.\n\n## Support\n\nProblems, questions, and feature requests can be opened on [GitHub Issues](https://github.com/NVIDIA/warp/issues).\n\nThe Warp team also monitors the **#warp** channel on the public [Omniverse Discord](https://discord.com/invite/nvidiaomniverse) server, come chat with us!\n\n## Versioning\n\nVersions take the format X.Y.Z, similar to [Python itself](https://devguide.python.org/developer-workflow/development-cycle/#devcycle):\n\n* Increments in X are reserved for major reworks of the project causing disruptive incompatibility (or reaching the 1.0 milestone).\n* Increments in Y are for regular releases with a new set of features.\n* Increments in Z are for bug fixes. In principle, there are no new features. Can be omitted if 0 or not relevant.\n\nThis is similar to [Semantic Versioning](https://semver.org/) but is less strict regarding backward compatibility.\nLike with Python, some breaking changes can be present between minor versions if well-documented and gradually introduced.\n\nNote that prior to 0.11.0, this schema was not strictly adhered to.\n\n## License\n\nWarp is provided under the NVIDIA Software License, please see [LICENSE.md](./LICENSE.md) for full license text.\n\n## Contributing\n\nContributions and pull requests from the community are welcome and are taken under the\nterms described in the **Feedback** section of [LICENSE.md](LICENSE.md#9-feedback).\n[CONTRIBUTING.md](./CONTRIBUTING.md) provides additional information on how to open a pull request for Warp.\n\n## Citing\n\nIf you use Warp in your research, please use the following citation:\n\n```bibtex\n@misc{warp2022,\ntitle= {Warp: A High-performance Python Framework for GPU Simulation and Graphics},\nauthor = {Miles Macklin},\nmonth = {March},\nyear = {2022},\nnote= {NVIDIA GPU Technology Conference (GTC)},\nhowpublished = {\\url{https://github.com/nvidia/warp}}\n}\n```\n","funding_links":[],"categories":["Python","Simulation","Cuda","📚 Learning \u0026 Resources","其他_机器视觉"],"sub_categories":["Dough","网络服务_其他"],"project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FNVIDIA%2Fwarp","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FNVIDIA%2Fwarp","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FNVIDIA%2Fwarp/lists"}