Skip to content

EXPERIMENTAL ONLY Clone of PR #2034#2075

Draft
rwgk wants to merge 9 commits into
NVIDIA:mainfrom
rwgk:cudla-bindings_review_rwgk
Draft

EXPERIMENTAL ONLY Clone of PR #2034#2075
rwgk wants to merge 9 commits into
NVIDIA:mainfrom
rwgk:cudla-bindings_review_rwgk

Conversation

@rwgk
Copy link
Copy Markdown
Contributor

@rwgk rwgk commented May 12, 2026

Clone of PR #2034

NOT FOR MERGING

EXPERIMENTAL ONLY

nikshayshrivastava and others added 7 commits May 5, 2026 23:27
Generated from cudla.h using cybind.

Files added:
- cycudla.pxd/pyx: Cython layer exposing C header types and functions
- cudla.pxd/pyx: lowpp Python layer with POD classes, enums, and wrappers
- _internal/cudla.pxd, cudla_linux.pyx, cudla_windows.pyx: dynamic library loading
- docs/source/module/cudla.rst: API documentation
- tests/cudla/: pytest unit tests for enums, POD types, error handling,
  API surface, and hardware-gated function tests (verified on L4T/Orin)

Build/CI updates:
- pyproject.toml: added cudla to cuda-toolkit optional dependencies
- .github/actions/fetch_ctk/action.yml: added libcudla to CTK components
- docs/source/api.rst: added cudla to toctree
Capture the documented API, standalone mode, and event-wrapper semantics we expect so CI can surface the current cuDLA binding gaps on hardware-backed runs.
@copy-pr-bot
Copy link
Copy Markdown
Contributor

copy-pr-bot Bot commented May 12, 2026

This pull request requires additional validation before any workflows can run on NVIDIA's runners.

Pull request vetters can view their responsibilities here.

Contributors can view more details about this message here.

@github-actions github-actions Bot added CI/CD CI/CD infrastructure cuda.bindings Everything related to the cuda.bindings module labels May 12, 2026
@rwgk
Copy link
Copy Markdown
Contributor Author

rwgk commented May 12, 2026

/ok to test

@copy-pr-bot
Copy link
Copy Markdown
Contributor

copy-pr-bot Bot commented May 12, 2026

/ok to test

@rwgk, there was an error processing your request: E1

See the following link for more information: https://docs.gha-runners.nvidia.com/cpr/e/1/

@rwgk
Copy link
Copy Markdown
Contributor Author

rwgk commented May 12, 2026

/ok to test dbecd15

@rwgk rwgk mentioned this pull request May 13, 2026
2 tasks
CI currently requests components like libcudla on lanes where NVIDIA does not publish them, so fetch_ctk fails before the build or tests start. Move the redistrib resolution into ci/tools, prune each lane to the components and relative paths that actually exist for its host platform and CUDA version, and validate that remote metadata is fetched only over HTTPS.
@rwgk
Copy link
Copy Markdown
Contributor Author

rwgk commented May 13, 2026

/ok to test 87d76a6

@github-actions
Copy link
Copy Markdown

The Linux local test lanes resolve the repo through the runtime workspace mount rather than the host-side checkout path, so the helper script must be launched from GITHUB_WORKSPACE. This lets those lanes reach the intended cuDLA regression failures instead of aborting in mini-CTK setup.
@rwgk
Copy link
Copy Markdown
Contributor Author

rwgk commented May 13, 2026

/ok to test 647ff82

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

CI/CD CI/CD infrastructure cuda.bindings Everything related to the cuda.bindings module

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants