Story simple matmul #13897
Closed
Story simple matmul #13897
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 commit introduces two main changes:
1. A new section in README.md providing a user-friendly guide on how to:
* Select a small model from Hugging Face (`microsoft/phi-2` as an example).
* Download and convert the model to GGUF format using the provided Python scripts.
* Run the converted model using `llama-cli`.
This aims to improve the onboarding experience for new users.
2. The `llamafile_sgemm` CPU matrix multiplication kernel in `ggml/src/ggml-cpu/llamafile/sgemm.cpp` has been replaced with a basic, triple-nested loop implementation.
This was done for demonstrative and educational purposes as you requested, to show a very simple version of the kernel. The original optimized code has been commented out for reference.
This commit updates the README.md to provide more detailed instructions for building llama.cpp with CUDA support. It also adds a troubleshooting subsection to help you address common build issues, such as the `std_function.h` parameter pack error that can occur due to compiler/CUDA version incompatibilities. The changes include: - More specific CMake commands for building with CUDA. - A direct link to NVIDIA's documentation for finding GPU compute capabilities. - Guidance on checking compiler/CUDA compatibility and consulting community resources for build error solutions.
github-actions
bot
added
the
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Outdated suggestions cannot be applied.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.
Make sure to read the contributing guidelines before submitting a PR