From 154e0d75fccf1784fe9ff6fd76a630b66563da3d Mon Sep 17 00:00:00 2001 From: Kawrakow <48489457+ikawrakow@users.noreply.github.com> Date: Sat, 27 Jul 2024 07:55:01 +0200 Subject: Merge mainline llama.cpp (#3) * Merging mainline - WIP * Merging mainline - WIP AVX2 and CUDA appear to work. CUDA performance seems slightly (~1-2%) lower as it is so often the case with llama.cpp/ggml after some "improvements" have been made. * Merging mainline - fix Metal * Remove check --------- Co-authored-by: Iwan Kawrakow --- gguf-py/gguf/__init__.py | 2 ++ 1 file changed, 2 insertions(+) (limited to 'gguf-py/gguf/__init__.py') diff --git a/gguf-py/gguf/__init__.py b/gguf-py/gguf/__init__.py index ea5146b1..243defc4 100644 --- a/gguf-py/gguf/__init__.py +++ b/gguf-py/gguf/__init__.py @@ -5,3 +5,5 @@ from .gguf_writer import * from .quants import * from .tensor_mapping import * from .vocab import * +from .utility import * +from .metadata import * -- cgit v1.2.3