[GH-ISSUE #423] llamma.cpp breaking change deprecating GGML in favor of GGUF #25955

Closed
opened 2026-04-22 01:49:31 -05:00 by GiteaMirror · 2 comments
Owner

Originally created by @jkleckner on GitHub (Aug 26, 2023).
Original GitHub issue: https://github.com/ollama/ollama/issues/423

Note that the upstream llama.cpp project has now completely deprecated GGML in favor of GGUF [1].

How should the repository and user models adapt to this?

[1] https://github.com/ggerganov/llama.cpp/pull/2398

Originally created by @jkleckner on GitHub (Aug 26, 2023). Original GitHub issue: https://github.com/ollama/ollama/issues/423 Note that the upstream llama.cpp project has now completely deprecated GGML in favor of GGUF [1]. How should the repository and user models adapt to this? [1] https://github.com/ggerganov/llama.cpp/pull/2398
Author
Owner

@BruceMacD commented on GitHub (Aug 26, 2023):

We're going to be adding the gguf runner very soon. We're going to make the transition such that Ollama can still run both gguf and older ggml formats, this means the transition will not require any action on the user's part.

<!-- gh-comment-id:1694413896 --> @BruceMacD commented on GitHub (Aug 26, 2023): We're going to be adding the gguf runner very soon. We're going to make the transition such that Ollama can still run both gguf and older ggml formats, this means the transition will not require any action on the user's part.
Author
Owner

@jkleckner commented on GitHub (Aug 26, 2023):

Cool, thanks!

<!-- gh-comment-id:1694417843 --> @jkleckner commented on GitHub (Aug 26, 2023): Cool, thanks!
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: github-starred/ollama#25955