Skip to content

test: tolerate unsupported NVML clock offsets on new GPUs - #3022

Merged
rwgk merged 1 commit into
NVIDIA:mainfrom
rwgk:nvml_test_fix_clock_offsets
Oct 6, 2026
Merged

rwgk merged 1 commit into
NVIDIA:mainfrom
rwgk:nvml_test_fix_clock_offsets

Conversation

@rwgk

@rwgk rwgk commented Oct 5, 2026

Copy link
Copy Markdown
Contributor

Description

NVML can reject offsets for a clock domain such as memory on GB300 even when the GPU architecture is recent. Treat that capability as optional in test_clock.

See also:

  • nvbug 6814458 (SWQA validated the fix already)

NVML can reject offsets for a clock domain such as memory on GB300 even when the GPU architecture is recent. Treat that capability as optional in test_clock. Addresses nvbug 6814458.
@rwgk rwgk added this to the cuda.core next milestone Oct 5, 2026
@rwgk
rwgk requested a review from mdboom October 5, 2026 18:32
@rwgk rwgk self-assigned this Oct 5, 2026
@rwgk rwgk added bug Something isn't working cuda.core Everything related to the cuda.core module labels Oct 5, 2026
@github-actions

github-actions Bot commented Oct 5, 2026 •

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

@rwgk
rwgk merged commit 7caa370 into NVIDIA:main Oct 6, 2026
230 of 233 checks passed
@rwgk
rwgk deleted the nvml_test_fix_clock_offsets branch October 6, 2026 06:40
github-actions Bot pushed a commit that referenced this pull request Oct 7, 2026
Removed preview folders for the following PRs:
- PR #3022
- PR #3023
- PR #3027
- PR #3029
- PR #3036
- PR #3039
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

bug Something isn't working cuda.core Everything related to the cuda.core module

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants