{"full_name":"taichi-dev/taichi","owner":"taichi-dev","name":"taichi","shard":"1","url":"https://github.com/taichi-dev/taichi","description":"Productive, portable, and performant GPU programming in Python.","homepage":"https://taichi-lang.org","topics":["taichi","differentiable-programming","gpu-programming","sparse-computation","gpu","computer-graphics"],"tag_pages":["gpu"],"language":"C++","license":"Apache-2.0","avatar":"https://avatars.githubusercontent.com/u/33354891?v=4","created_at":"2016-11-24T10:00:05Z","pushed_at":"2026-10-05T20:58:47Z","metrics":{"stars":28461,"forks":2391,"watchers":384,"issues":2762,"prs":5915,"releases":118,"issues_open":879,"issues_closed":1883,"prs_open":47,"prs_closed":677,"prs_merged":5191,"discussions":106},"growth":{"day":{"stars":0,"forks":-1,"base_day":"2026-11-15"},"week":{"stars":7,"forks":-3,"base_day":"2026-11-04"},"month":{"stars":47,"forks":0,"base_day":"2026-10-17"}},"history":{"dates":["2026-09-06","2026-09-07","2026-09-08","2026-09-09","2026-09-10","2026-09-11","2026-09-12","2026-09-13","2026-09-14","2026-09-15","2026-09-16","2026-09-17","2026-09-18","2026-09-19","2026-09-20","2026-09-21","2026-09-22","2026-09-23","2026-09-24","2026-09-25","2026-09-26","2026-09-27","2026-09-28","2026-09-29","2026-09-30","2026-10-01","2026-10-02","2026-10-03","2026-10-04","2026-10-05","2026-10-06","2026-10-07","2026-10-08","2026-10-09","2026-10-10","2026-10-11","2026-10-12","2026-10-13","2026-10-14","2026-10-15","2026-10-16","2026-10-17","2026-10-18","2026-10-19","2026-10-20","2026-10-21","2026-10-22","2026-10-23","2026-10-24","2026-10-25","2026-10-26","2026-10-27","2026-10-28","2026-10-29","2026-10-30","2026-10-31","2026-11-01","2026-11-02","2026-11-03","2026-11-04","2026-11-10","2026-11-11","2026-11-12","2026-11-13","2026-11-14","2026-11-15","2026-11-16"],"stars":[28360,28360,28363,28361,28362,28364,28367,28369,28370,28369,28373,28373,28372,28373,28376,28377,28377,28377,28377,28379,28383,28384,28384,28385,28390,28396,28396,28397,28399,28403,28402,28403,28403,28406,28407,28407,28408,28410,28410,28414,28412,28414,28415,28419,28423,28425,28421,28423,28425,28426,28428,28428,28427,28426,28428,28429,28429,28438,28448,28454,28455,28458,28457,28457,28459,28461,28461],"forks":[2385,2386,2386,2387,2388,2388,2388,2389,2389,2389,2389,2389,2389,2389,2389,2389,2389,2389,2389,2389,2389,2389,2388,2388,2388,2389,2390,2389,2389,2389,2390,2391,2391,2389,2389,2389,2389,2389,2390,2390,2391,2391,2390,2390,2390,2390,2390,2391,2390,2390,2390,2391,2391,2391,2391,2391,2391,2391,2392,2394,2392,2392,2392,2392,2392,2392,2391],"watchers":[391,392,392,392,392,392,392,392,392,392,392,392,392,392,392,392,392,392,392,392,392,392,392,392,392,392,392,392,392,390,388,389,389,389,389,389,389,389,389,389,389,389,389,389,389,389,389,389,389,384,384,384,384,385,385,385,385,385,385,385,null,384,384,384,384,384,384],"issues_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,879,879,879,879,879,879],"prs_open":[null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,null,47,47,47,47,47,47]},"boards":{},"same_owner":[],"issues":[{"number":4857,"title":"Polish and officially release quantized types","comments":42,"created_at":"2022-04-26T01:51:02Z"},{"number":412,"title":"AMDGPU backend","comments":35,"created_at":"2020-01-30T00:51:12Z"},{"number":6434,"title":"Add support for AMDGPU","comments":31,"created_at":"2022-10-26T03:48:44Z"},{"number":1483,"title":"IDLE still doesn't work for me","comments":31,"created_at":"2020-07-13T01:21:30Z"},{"number":711,"title":"[OpenGL] Sparse data structure support","comments":26,"created_at":"2020-04-05T06:54:38Z"},{"number":4631,"title":"[RFC] [SIMT] Add CUDA warp-level intrinsics to Taichi","comments":25,"created_at":"2022-03-25T15:16:38Z"},{"number":5436,"title":"Using Taichi from Julia","comments":22,"created_at":"2022-07-16T09:04:36Z"},{"number":3781,"title":"[RFC] Taichi on Javascript","comments":22,"created_at":"2021-12-12T20:14:46Z"}],"discussions":[{"number":8798,"title":"Squarenet gridification as a bridge between unstructured point clouds and Taichi stencil kernel","comments":0,"category":"Ideas","created_at":"2026-07-20T16:19:10Z"},{"number":8782,"title":"LPBF Melt Pool Simulation","comments":0,"category":"Q&A","created_at":"2026-01-29T17:16:52Z"},{"number":8776,"title":"Struct function get_ch_S0_to_S15 not found.","comments":1,"category":"Q&A","created_at":"2025-12-05T12:05:47Z"},{"number":8771,"title":"I have a data_oriented class, when I profile my test, I found one kernel function in this class is compiled hundreds of time, why is that?","comments":0,"category":"Q&A","created_at":"2025-11-04T12:40:40Z"},{"number":8766,"title":"Is SNode layout mutable at compile/runtime? Any ongoing work on automatic SNode layout optimization?","comments":0,"category":"Q&A","created_at":"2025-10-25T14:56:56Z"},{"number":8679,"title":"Redeem my cpu & Apple Cash contributions","comments":0,"category":"Docs","created_at":"2025-04-21T08:15:37Z"},{"number":8665,"title":"Are dynamic fields as a struct member supported?","comments":1,"category":"Q&A","created_at":"2025-03-23T19:18:20Z"},{"number":8642,"title":"Multiple Layers of For-Loops","comments":1,"category":"Q&A","created_at":"2025-02-24T07:06:14Z"}],"latest_release":{"name":"v1.7.4","tag":"v1.7.4","published_at":"2025-07-31T15:32:07Z","body":"** Warning: tag sparse matrix undefined in the \"details\" dict. Please include the tag into \"details\", unless the tag is a typo.\nHighlights:\n   - **Build system**\n      - Revert \"Drop OpenGL build (#8751)\" (#8753) (by **Proton**)\n      - Drop OpenGL build (#8751) (by **Proton**)\n      - Use brew clang compiler on mac (#8704) (by **Hugh Perkins**)\n      - Update VMA and Vulkan-Headers to support Vulkan 1.3 (#8680) (by **Antonio Ferreras**)\n   - **Examples**\n      - Factorize cpp examples into separate executables (#8709) (by **Hugh Perkins**)\n   - **GUI**\n      - Support ndarray input (#8661) (by **白定**)\n   - **IR optimization passes**\n      - Remove redundant cfg optimization, to fix struct vec crash bug (#8691) (by **Hugh Perkins**)\n   - **Unified Device API**\n      - Fix the Unified Allocator to no longer return first two allocations as dupes (#8705) (by **Hugh Perkins**)\n\nFull changelog:\n   - [misc] Bump to v1.7.4 (by **Proton**)\n   - [ci] Sync Near Cache needs a python env (by **Proton**)\n   - [ci] Fix Windows torch version (by **Proton**)\n   - [ir] Sanitize SPIRV debugprintf string (#8752) (by **Proton**)\n   - [ci] Windows needs Vulkan SDK (#8754) (by **Proton**)\n   - [Build] Revert \"Drop OpenGL build (#8751)\" (#8753) (by **Proton**)\n   - [Build] Drop OpenGL build (#8751) (by **Proton**)\n   - [build] Update minimum requirement for CMAKE (#8703) (by **Linull/李林**)\n   - [build] Add Python 3.13 build (#8748) (by **Proton**)\n   - [build] Identify aarch64 wheels (#8716) (by **Johnny**)\n   - [build] Update setup function to use Miniforge and correct download URLs (#8719) (by **Johnny**)\n   - [build] Update Vulkan SDK version (#8749) (by **T.Yamada**)\n   - [build] Update sccache download URLs to version 0.10.0 for various plat… (#8717) (by **Johnny**)\n   - [build] Replace libtinfo-dev with libncurses-dev in package dependencies (#8718) (by **Johnny**)\n   - [ci] Migrate to new threading interface (#8731) (by **Emmanuel Ferdman**)\n   - [ci] Upgrade setup-python actions (#8739) (by **Proton**)\n   - [ci] Drop support of Python < 3.9 (#8737) (by **Proton**)\n   - [build] Add support for extracting .tar.xz archives in dep.py (#8721) (by **Johnny**)\n   - [Rhi] [bug] Fix the Unified Allocator to no longer return first two allocations as dupes (#8705) (by **Hugh Perkins**)\n   - [Build] Use brew clang compiler on mac (#8704) (by **Hugh Perkins**)\n   - [Example] Factorize cpp examples into separate executables (#8709) (by **Hugh Perkins**)\n   - [lang] Add SNode.snode_tree_id (#8697) (by **Hugh Perkins**)\n   - [misc] Bug report template instructions no longer render in final bug report (#8699) (by **Hugh Perkins**)\n   - [Opt] Remove redundant cfg optimization, to fix struct vec crash bug (#8691) (by **Hugh Perkins**)\n   - [ci] Do not setup Vulkan SDK (#8692) (by **Proton**)\n   - [misc] Fix cannot name an alias template, fixes #8683 (by **Hugh Perkins**)\n   - [build] [mac] Fix mac build symbol export failure (#8690) (by **Hugh Perkins**)\n   - [ci] Switch git proxy (#8681) (by **Proton**)\n   - [Build] Update VMA and Vulkan-Headers to support Vulkan 1.3 (#8680) (by **Antonio Ferreras**)\n   - [GUI] Support ndarray input (#8661) (by **白定**)\n   - [ci] Bump minimum python version to 3.9 to align with pytorch (#8676) (by **Bob Cao**)\n   - [vulkan] Let VMA grab fptrs itself (#8672) (by **Bob Cao**)\n   - [ci] Fix pre-commit rants, disable deprecated GitHub integration (#8671) (by **Proton**)\n   - [amdgpu] Calculate mcpu_ and compute_capability_ properly and with ROCm 6 compat (#8667) (by **Gavin Zhao**)\n   - [ci] Disable paddle tests, limit cmake version (#8670) (by **Proton**)\n   - [ci] Chasing migrated bot master (#8657) (by **Proton**)\n   - [doc] Fix typo in README.md (#8612) (by **Ikko Eltociear Ashimine**)\n   - [ci] Fixing releasing (#8651) (by **Proton**)\n   - [ci] Upgrade deprecated (up|down)load-artifacts@v3 actions to v4 (#8645) (by **Proton**)\n   - [Sparse Matrix] Fix dimension mismatch error in sparse matrix multiplication (#8644) (by **peng","is_prerelease":false},"readme":true,"readme_zh":false,"news":[],"stale":false,"snapshot_at":"2026-11-16T09:23:14Z","history_start":"2026-09-06"}