Skip to content

Prepare gpufl client 1.3.0rc6 - #175

Merged
CodingInAVan merged 1 commit into
mainfrom
release/v1.3.0rc6
Oct 20, 2026
Merged

CodingInAVan merged 1 commit into
mainfrom
release/v1.3.0rc6

Conversation

@CodingInAVan

Copy link
Copy Markdown
Contributor

Bumps the version to 1.3.0rc6. This commit touches only CMakeLists.txt GPUFL_VERSION_SUFFIX, pyproject.toml and python/gpufl/__init__.py. release.yml rewrites only the numeric CMake version from the tag, so the suffix has to be committed.

rc6 contains:

  • Capture PTX that programs load at run time #174: PTX that a program hands to the driver at run time is captured, from cuModuleLoadData, cuModuleLoadDataEx and cuLinkAddData, after a successful load. Rust (cuda-oxide) sessions get PTX beside SASS, as CUDA C++ sessions already do. reset() now clears the PTX state, so a later session in the same process runs cuobjdump again.

After merge: tag the merge commit v1.3.0rc6. That publishes to PyPI and the Jupyter image.

@CodingInAVan
CodingInAVan merged commit ad1d717 into main Oct 20, 2026
11 checks passed
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant