Skip to content

cuda.core: refresh frozen CUresult explanation table for CUDA 13.3 - #2383

Merged
leofang merged 4 commits into
NVIDIA:mainfrom
Symbioose:fix/frozen-curesult-table-13.3
Sep 2, 2026
Merged

cuda.core: refresh frozen CUresult explanation table for CUDA 13.3#2383
leofang merged 4 commits into
NVIDIA:mainfrom
Symbioose:fix/frozen-curesult-table-13.3

Conversation

@Symbioose

Copy link
Copy Markdown
Contributor

Description

closes #2370

This regenerates the frozen CUresult fallback explanation table
(driver_cu_result_explanations_frozen.py) for CUDA 13.3, which added
CUDA_ERROR_GRAPH_RECAPTURE_FAILURE (code 918). This table is only used
as a fallback for cuda-bindings versions that don't yet expose usable
enum __doc__ text (see enum_explanations_helpers.py), but it needs to
stay in sync with new CUDA Toolkit error codes so those users still get
an informative error message.

Changes:

  • Added the 918: "..." entry to _FALLBACK_EXPLANATIONS and bumped the
    version comment to CUDA Toolkit v13.3.
  • Added a tripwire test (test_frozen_driver_table_covers_all_curesult_members)
    that compares cuda.bindings.driver.CUresult members against the frozen
    table keys, so future toolkit bumps that add new driver error codes are
    caught automatically.
  • Documented the refresh step in the cuda.core release checklist
    (RELEASE-core.md).

Checklist

  • New or existing tests cover these changes.
  • The documentation is up to date with these changes.

@copy-pr-bot

copy-pr-bot Bot commented Jul 17, 2026

Copy link
Copy Markdown
Contributor

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.core Everything related to the cuda.core module labels Jul 17, 2026
@Symbioose

Symbioose commented Jul 17, 2026

Copy link
Copy Markdown
Contributor Author

Hi @leofang, this is ready for review. First-time contributor, let me know if I'm missing anything 👍, and could you add an assignee/milestone so the metadata check passes? Thanks!

@mdboom

mdboom commented Jul 21, 2026

Copy link
Copy Markdown
Contributor

/ok to test 2c21305

@mdboom
mdboom enabled auto-merge (squash) July 21, 2026 18:05
@github-actions

This comment has been minimized.

@mdboom

mdboom commented Jul 29, 2026

Copy link
Copy Markdown
Contributor

/ok to test e5511c8

@kkraus14 kkraus14 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.

These fallback explanations are only used when we didn't have a richer explanation of the result code available as a __doc__ property, which started with cuda-bindings 12.9.6 / 13.2.0. Since the result code being added is specific to new CUDA 13.3 features it can't be returned in situations where the fallback explanations are being used.

We could still merge this to keep the fallbacks up to date in case a new CUDA release somehow returns a new error code from an existing API, but if we wish to merge this both the driver and runtime explanation need to be updated.

@mdboom
mdboom disabled auto-merge August 11, 2026 12:22
@leofang

leofang commented Sep 2, 2026

Copy link
Copy Markdown
Member

This seems to make sense to me. I'll run CI and then admin-merge.

@leofang

leofang commented Sep 2, 2026

Copy link
Copy Markdown
Member

/ok to test 82e40fc

@leofang leofang added this to the cuda.core 1.2.0 milestone Sep 2, 2026
@leofang
leofang enabled auto-merge (squash) September 2, 2026 18:15
@leofang
leofang disabled auto-merge September 2, 2026 19:35
@leofang
leofang merged commit 3df6115 into NVIDIA:main Sep 2, 2026
109 of 112 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

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

Projects

None yet

Development

Successfully merging this pull request may close these issues.

[MNT] cuda.core: refresh the frozen CUresult explanation table for CUDA 13.3

4 participants