Skip to content

chore: adjust comment in Dockerfile regarding RTX5090 support#316

Open
kyteinsky wants to merge 1 commit into
masterfrom
chore/explicit-support-for-cuda-gpus
Open

chore: adjust comment in Dockerfile regarding RTX5090 support#316
kyteinsky wants to merge 1 commit into
masterfrom
chore/explicit-support-for-cuda-gpus

Conversation

@kyteinsky

Copy link
Copy Markdown
Contributor

Assisted-by: Github Copilot:claude-sonnet-4-6

fixes: #305

🤖 AI (if applicable)

  • The content of this PR was partly or fully generated using AI

Signed-off-by: kyteinsky <kyteinsky@gmail.com>
Assisted-by: Github Copilot:claude-sonnet-4-6
@kyteinsky kyteinsky requested a review from marcelklehr as a code owner June 17, 2026 05:32
Comment thread Dockerfile
# Real cubins for all shipping GPU generations through Blackwell (sm_100),
# plus one forward-compatible PTX target to keep wheel size manageable.
# CMAKE_CUDA_ARCHITECTURES is intentionally not set here. llama.cpp's CMake
# selects sensible defaults based on the detected CUDA toolkit version:

Copy link
Copy Markdown
Member

Choose a reason for hiding this comment

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

mmh, but this is at build time, right? so it does not depend on the CUDA version that the admin has but on the CUDA version of the CUDA_DEVEL_IMAGE, correct?

Copy link
Copy Markdown
Contributor Author

Choose a reason for hiding this comment

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

yep, and we depend on llama.cpp to make the correct choice of cubins to bake in, so we don't have to check and adjust it when the cuda version changes.
we could but it already exists so I didn't bother.

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.

RTX5090 Blackwell support

2 participants