I'm glad the llama.cpp and the ggml backing are getting consistent reliable economic support. I'm glad that ggerganov is getting rewarded for making such excellent tools.
I am somewhat anxious about "integration with the Hugging Face transformers library" and possible python ecosystem entanglements that might cause. I know llama.cpp and ggml already have plenty of python tooling but it's not strictly required unless you're quantizing models yourself or other such things.
I am somewhat anxious about "integration with the Hugging Face transformers library" and possible python ecosystem entanglements that might cause. I know llama.cpp and ggml already have plenty of python tooling but it's not strictly required unless you're quantizing models yourself or other such things.