Skip to content

Fix #2363: Support using bundled headers with NVRTC 13.3+. - #2753

Merged
rparolin merged 1 commit into
NVIDIA:mainfrom
mdboom:bundled-headers
Sep 2, 2026
Merged

Fix #2363: Support using bundled headers with NVRTC 13.3+.#2753
rparolin merged 1 commit into
NVIDIA:mainfrom
mdboom:bundled-headers

Conversation

@mdboom

@mdboom mdboom commented Sep 2, 2026

Copy link
Copy Markdown
Contributor

This adds support for using bundled headers, as provided in NVRTC 13.3.

This sidesteps a lot of the complexity of what #2363 suggested by just using the --use-bundled-headers commandline argument, rather than making API calls directly. It handles updating to a new version (only when necessary) and adding the installed-header location to the include paths appropriately, so we don't have to re-invent those wheels.

This always uses a user-global cache directory (following the platform-specific conventions for those). There is a small refactor here to pull out the logic for that that already existed for program_cache into a general utility that this and the program_cache both use.

@mdboom
mdboom requested a review from rparolin September 2, 2026 15:28
@github-actions github-actions Bot added the cuda.core Everything related to the cuda.core module label Sep 2, 2026
@mdboom mdboom self-assigned this Sep 2, 2026
@mdboom mdboom added the enhancement Any code-related improvements label Sep 2, 2026
@mdboom mdboom added this to the cuda.core 1.2.0 milestone Sep 2, 2026
@github-actions

This comment has been minimized.

@rparolin rparolin left a comment

Copy link
Copy Markdown
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

lgtm

@rparolin
rparolin merged commit 858fb2f into NVIDIA:main Sep 2, 2026
112 of 113 checks passed
@github-actions

github-actions Bot commented Sep 2, 2026

Copy link
Copy Markdown
Doc Preview CI
Preview removed because the pull request was closed or merged.

@leofang leofang mentioned this pull request Sep 2, 2026
2 tasks
leofang added a commit that referenced this pull request Sep 2, 2026
* Prepare cuda.core v1.2.0 release

Fill remaining user-visible entries in the 1.2.0 release notes and add
1.1.1 and 1.2.0 to the docs version switcher. Version is derived from
the git tag via setuptools-scm, so no pyproject.toml bump is needed.

New features documented:
- ProgramOptions.use_bundled_headers for NVRTC 13.3+ (#2753 closes #2363)
- cuda-gdb source display for JIT-compiled kernels (#2678, #2679)

Fixes and enhancements documented:
- PinnedMemoryResource host-pool validation at construction (#2487)
- is_host_accessible for NUMA-located VMM (#2503)
- Graph predecessor/successor query truncation on large graphs (#2587)
- Per-domain NVML clock queries treated as independently optional (#2651)
- Temperature threshold checks forward-compat with unknown archs (#2488)
- import cuda.core non-integer opt-out crash (#2535)
- Frozen CUresult explanation table refreshed for CUDA 13.3 (#2383)

-- Leo's bot

* Update cuda_core/docs/source/release/1.2.0-notes.rst

Co-authored-by: Michael Droettboom <[email protected]>

---------

Co-authored-by: Michael Droettboom <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

cuda.core Everything related to the cuda.core module enhancement Any code-related improvements

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants