git clone https://github.com/b4rtaz/distributed-llama.gitmake dllamasudo nice -n -20 ./dllama inference --model /path/to/dllama_model_llama3-70b-instruct_q40.m --tokenizer /path/to/dllama_tokenizer_llama3.t --weights-float-type q40 --buffer-float-type q80 --prompt "Hello world" --steps 16 --nthreads 4