LLaMA now goes faster on CPUs(justine.lol)
1286 points by lawrencechen | 413 comments
Justine Tunney's blog post describing 84 new matrix multiplication kernels that make llamafile prompt evaluation 30-500% faster on CPUs than llama.cpp.
1286 points by lawrencechen | 413 comments
Justine Tunney's blog post describing 84 new matrix multiplication kernels that make llamafile prompt evaluation 30-500% faster on CPUs than llama.cpp.
300 points by Abishek_Muthian | 183 comments