alt Hacker NewsI imagine how advantageous it would be to have something like llama.cpp encoded on a chip instead, allowing us to run more than a single model. It would be slower than Jimmy, for sure, but depending on the speed, it could be an acceptable trade-off.
I imagine how advantageous it would be to have something like llama.cpp encoded on a chip instead, allowing us to run more than a single model. It would be slower than Jimmy, for sure, but depending on the speed, it could be an acceptable trade-off.