I've added a detailed onboarding guide for llama.cpp and ggml. #14063
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
This guide provides a comprehensive introduction for you, particularly if you have a CS50-level programming background. It covers: - What llama.cpp and ggml are, and their core benefits. - A detailed explanation of ggml's fundamental concepts: tensors, computation graphs, contexts, backends, and quantization. - The structure and purpose of the GGUF file format. - How llama.cpp utilizes ggml for inference and hardware abstraction. - Steps for setting up a basic development environment. - A detailed walkthrough of how to contribute a new backend to ggml, including understanding the `ggml_backend.h` interface, implementing necessary functions, and testing. This section uses AMD XDNA 2 as a conceptual example. - Tips for further learning and successful contribution. The guide aims to lower the barrier to entry for understanding and contributing to the llama.cpp and ggml ecosystems.
github-actions
bot
added
the
documentation
Author
|
Sorry for the trouble I thought I was making a pull request to my own fork instead of ggml |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
This guide provides a comprehensive introduction for you, particularly if you have a CS50-level programming background.
It covers:
ggml_backend.hinterface, implementing necessary functions, and testing. This section uses AMD XDNA 2 as a conceptual example.The guide aims to lower the barrier to entry for understanding and contributing to the llama.cpp and ggml ecosystems.
Make sure to read the contributing guidelines before submitting a PR