Skip to content

Make Kompute error verbose about unsupported types #10034

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Closed
wants to merge 1 commit into from

Conversation

ericcurtin
Copy link
Collaborator

Print the arch and quantization as strings.

Print the arch and quantization as strings.
@@ -9127,7 +9127,7 @@ static int llama_model_load(const std::string & fname, llama_model & model, llam
)
)) {
// TODO(cebtenzzre): propagate this error outside of llama_load_model_from_file
LLAMA_LOG_WARN("%s: disabling Kompute due to unsupported model arch or quantization\n", __func__);
LLAMA_LOG_WARN("%s: disabling Kompute due to unsupported model arch (%s) or quantization (%s)\n", __func__, LLM_ARCH_NAMES.at(model.arch), llama_model_ftype_name(model.ftype).c_str());
Copy link
Member

Choose a reason for hiding this comment

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

This warning will be removed in #10026, since the llama model loader will be able to offload weights only to backends that can actually use them, which should make this unnecessary. However, that PR will also remove support for backends that do not implement the backend reg and device interfaces, and currently only Kompute doesn't. If there is interest in keeping this backend in llama.cpp, it should be updated to implement these interfaces.

Copy link
Collaborator Author

Choose a reason for hiding this comment

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

Oh ok I can close this

@ericcurtin ericcurtin closed this Oct 24, 2024
@ericcurtin ericcurtin deleted the kompute-debug branch October 24, 2024 18:13
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants