Skip to content

Conversation

@rgerganov
Copy link
Collaborator

Add RPC_CMD_HELLO for getting the version of the protocol implemend by the server. Follow the semantic versioning rules at https://semver.org

Hopefully this bring better user experience when we make breaking changes at the protocol level and avoid issues like #12465

@github-actions github-actions bot added examples ggml changes relating to the ggml tensor library for machine learning labels Apr 15, 2025
@rgerganov
Copy link
Collaborator Author

@slaren Is there anything else we can do to make this future proof when ggml starts having versions?

@rgerganov rgerganov requested a review from slaren April 15, 2025 09:02
Copy link
Member

@slaren slaren left a comment

Choose a reason for hiding this comment

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

I don't think there is a way to make this future-proof for ggml versions at this point because we don't even know how ggml is going to be versioned. However, that shouldn't be a problem because once that is done, you can easily increase the version of the RPC protocol and make any changes that may be necessary.

I would suggest blocking clients that do not send the HELLO packet to prevent older versions from skipping the check entirely.

Add RPC_CMD_HELLO for getting the version of the protocol implemend by
the server. Follow the semantic versioning rules at https://semver.org

Hopefully this bring better user experience when we make breaking
changes at the protocol level and avoid issues like ggml-org#12465
@rgerganov rgerganov merged commit 2db9ba1 into ggml-org:master Apr 18, 2025
94 of 96 checks passed
colout pushed a commit to colout/llama.cpp that referenced this pull request Apr 21, 2025
Add RPC_CMD_HELLO for getting the version of the protocol implemend by
the server. Follow the semantic versioning rules at https://semver.org

Hopefully this bring better user experience when we make breaking
changes at the protocol level and avoid issues like ggml-org#12465
pockers21 pushed a commit to pockers21/llama.cpp that referenced this pull request Apr 28, 2025
Add RPC_CMD_HELLO for getting the version of the protocol implemend by
the server. Follow the semantic versioning rules at https://semver.org

Hopefully this bring better user experience when we make breaking
changes at the protocol level and avoid issues like ggml-org#12465
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

examples ggml changes relating to the ggml tensor library for machine learning

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants