Llama.cpp v0.1.0

(github.com)

28 points | by satvikpendem 2 hours ago ago

6 comments

  • ggerganov 10 minutes ago

    Didn't expect this to pop up here - please ignore for now. We are preparing official semantic versioning of llama.cpp and it's almost ready, but not quite.

    More info about the versioning process is here: https://github.com/ggml-org/ggml/discussions/1579

    • shrinks99 2 minutes ago

      That's really encouraging news. The per-commit versioning has been tricky to follow. Happy to see it!

  • tingletech an hour ago

    what's the significance of this? There is also a v0.1.1 from 4 hours ago, but these v0.1.x one's are on the releases tab https://github.com/ggml-org/llama.cpp/releases

    seems like stray tags?

    • rpdillon an hour ago

      Yeah, I think they are strays added by GitHub Actions, they don't line up with the actual version that's tracked inside the source code, which indicates v0.20.1:

      https://github.com/ggml-org/llama.cpp/commit/cea66f4c5a17255...

      • wccrawford 24 minutes ago

        2 releases back:

        ``` Add a "Create and push git tag" step to the release job, right before the "Create release" step. The tag is created with git tag and pushed with the deploy key already configured by the Clone step, instead of relying on the Releases API (action-create-release) to create it as a side effect.

        The tag is lightweight, matching all existing b release tags. The step is idempotent: if the tag already exists (e.g. on a re-run), creation and push are skipped. ```

        I think they just haven't configured the TAG part of that properly yet, so it created an incorrect tag the first run.

  • asveikau 31 minutes ago

    The github release pages for this project have me wondering who it is for. There are multiple releases per day. Also the Linux release binaries do not compile for CUDA.

    It's more reasonable for a lot of people to just follow master and build from source.