Comment by dmichulke
1 month ago
Forgive my ignorance but aren't they already on huggingface?
I assumed turboquant optimizations are already everywhere - in llama-cpp, or the quantization machinery of unsloth and the likes.
1 month ago
Forgive my ignorance but aren't they already on huggingface?
I assumed turboquant optimizations are already everywhere - in llama-cpp, or the quantization machinery of unsloth and the likes.
I forked it to also add rotorquant. This is a specific optimization that uses clifford rotors instead of static compile time random purmutation to store the activations. Reduces space and parameter count for the storage.