updated llama.cpp · utilityai/llama-cpp-rs@c85679b · GitHub

Commit

updated llama.cpp

Browse files

Loading branch information

Marcus Dunn committed Jan 21, 2024

1 parent 40d4b04 commit c85679b

llama-cpp-sys-2/llama.cpp

Submodule llama.cpp updated 12 files

+12 −0		CMakeLists.txt
+1 −0		README.md
+5 −4		convert-hf-to-gguf.py
+5 −9		convert-llama-ggml-to-gguf.py
+1 −2		convert-lora-to-ggml.py
+6 −4		convert-persimmon-to-gguf.py
+223 −414		convert.py
+6 −6		examples/perplexity/perplexity.cpp
+20 −14		ggml-backend.c
+5 −3		ggml-cuda.cu
+79 −66		llama.cpp
+1 −0		mypy.ini

0 comments on commit `c85679b`

Please sign in to comment.