FrRay
/
Intro-ops
forked from ccf-ai-infra/Intro-ops
0
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
34 Commits 2 Branches 0 Tags 11 MiB
Commit Graph

34 Commits

Author SHA1 Message Date
FrRay 9db686ad2d docs: add Mermaid diagrams, Jupyter Notebooks, and course scripts 
- docs/diagrams/: 4 Mermaid diagrams (grid-stride loop, thread grid, tree reduction, softmax pipeline)
- notebooks/: 6 Jupyter Notebooks (env setup, copy, vector_add, reduce_sum, softmax, benchmark)
- course/scripts/: 5 course scripts (framework + 4 operators, 5+10+3+2 format)
- fix: JSON encoding in notebooks (BOM removal, Chinese quotation marks)
- fix: troubleshooting.md softmax code example and tilelang-vs-cuda.md template declaration
 2026-06-05 15:15:54 +08:00
FrRay 3b3cb6af72 docs: add community infrastructure — glossary, FAQ, troubleshooting, learning path, PR guide, issue/PR templates, TileLang vs CUDA comparison, English phase1 guide 2026-06-05 12:35:56 +08:00
yutianyu 287867a34e build: add optional tilelang-metax validation mode 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-13 18:24:44 +08:00
yutianyu 9afe211d65 docs: streamline README and guides 
Co-Authored-By: wawahejun <hejunlbbc@gmail.com>
 2026-05-13 16:17:32 +08:00
yutianyu 7c6a5ed9aa feat: integrate CUTLASS CuTe-optimized copy for L40 (SM89) 
Add auto-fetch of CUTLASS third_party dependency in build script,
enable 128-bit vectorized TiledCopy kernel via CuTe for the NVIDIA
copy operator, and clean up build artifacts from version control.

Co-Authored-By: wawahejun <hejunlbbc@gmail.com>
 2026-05-13 15:39:29 +08:00
yutianyu c8ad11c277 refactor: unify elementwise runtime helpers 2026-05-12 16:23:06 +08:00
yutianyu 9271fed062 feat: add reusable elementwise relu support 2026-05-12 11:30:19 +08:00
yutianyu 757dbbec74 refactor: split operator headers into public and detail layers 2026-05-08 11:18:47 +08:00
yutianyu 6e02c3eb55 feat: add MACA-based MetaX backend support 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-08 09:49:13 +08:00
yutianyu ec8ed33b27 docs: add detailed info md 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu 6d1f205610 refactor: scaffold phase1 kernel skeletons 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu 7d94bb17f9 docs: add phase1 kernel writing guide 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu 9147a4821d feat: add kernel-focused benchmark timing harness 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu 346fd7db12 refactor: rename op tests and update benchmark entrypoint 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu a2cda3fda7 feat: add more shared test cases 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu e9a4c87564 docs: update guides for refactored python layout 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu dcf4d25896 refactor: split runtime internals and testing package 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu 1c5b1db200 refactor: consolidate benchmark entrypoint 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu 1368fa2886 docs: add Chinese README and operator guide 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu aec1073394 refactor: restructure Python package layout 
Group modules by responsibility:

- _runtime/: internal C ABI layer (loader, ctypes_bindings,
  prepared, tensor_view); underscore prefix signals non-public API
- testing/: test utilities split by concern (assertions, benchmark,
  profiler) instead of mixed in top-level files
- ops/__init__.py: per-operator registration; adding a new operator
  only requires one line here, not touching the top-level __init__
- operator_runtime/__init__.py: thin gateway that re-exports from ops/

External import paths for tests are unchanged:
operator_runtime.testing still exports require_cuda, assert_close,
cuda_time_ms, PerformanceResult

Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu fa2608e9b6 build: remove YAML-driven operator registration 
Replace the YAML manifest + Python code-generation pipeline with
CMake file(GLOB_RECURSE) auto-discovery. Operators are now registered
by directory convention (ops/<name>/nvidia/*.cu) rather than by
declaring sources and symbols in operator.yaml.

Deleted: ops/*/operator.yaml, cmake/GenerateOperators.cmake,
tools/generate_operator_artifacts.py, tools/operator_schema.yaml,
tools/validate_operator_manifest.py, operator_registry.py,
tests/test_manifest_contract.py

Modified: ops/CMakeLists.txt uses GLOB_RECURSE, requirements.txt
drops pyyaml

Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu e255552a94 chore: add requirements.txt and update README setup/validate instructions 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu 1759575ea7 refactor: organize per-operator test runners 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu 246e21f3d1 feat: unify example backends and shared test cases 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu 347421d28b refactor: reorganize operator benchmarks 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu e4ce213d65 refactor: split tilelang student kernels 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu 9db9af67b8 refactor: split nvidia operator kernels 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu fb59a60034 test: cover TileLang copy templates 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu dbe054c876 feat: add TileLang copy mode templates 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu 449075499b test: add runtime correctness and benchmark coverage 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu ce30e4b195 feat: scaffold operator runtime backends 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu 529e7fc7b7 docs: add training runtime guide and examples 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu ddbbc09019 chore: add project ignore rules 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00
yutianyu df83aafc05 feat: add cnb 
Co-authored-by: wawahejun <hejunlbbc@gmail.com>
 2026-05-05 16:50:18 +08:00