Skip to content

Conversation

ericcurtin
Copy link
Collaborator

Print the arch and quantization as strings.

Print the arch and quantization as strings.
)) {
// 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