CPU Inference of LLama 3.2

meta-llama / llama

Inference code for Llama models

Other

56.57k stars 9.59k forks source link

CPU Inference of LLama 3.2 #1184

Open FedorSymkin opened 1 month ago

FedorSymkin commented 1 month ago

Hello. I need CPU Inference of LLama 3.2, and I've found opened PR https://github.com/meta-llama/llama/pull/202 for it. Do you have plans to merge it? I could not find any mentions about CPU mode in main, so I assume this PR is still actual