llama.cpp updated · mgonzs13/llama_ros@46f3740 · GitHub

Commit

llama.cpp updated

Browse files

Loading branch information

mgonzs13 committed Jan 14, 2024

1 parent 9db8e49 commit 46f3740

llama_ros/llama_cpp

Submodule llama_cpp updated 19 files

+6 −2		CMakeLists.txt
+0 −9		Makefile
+0 −3		examples/CMakeLists.txt
+2 −2		examples/benchmark/benchmark-matmult.cpp
+0 −4		examples/metal/CMakeLists.txt
+0 −103		examples/metal/metal.cpp
+131 −2		examples/quantize/quantize.cpp
+14 −4		examples/server/server.cpp
+2 −53		ggml-metal.h
+24 −254		ggml-metal.m
+1,349 −68		ggml-quants.c
+11 −4		ggml-quants.h
+77 −33		ggml.c
+6 −3		ggml.h
+151 −52		llama.cpp
+1 −0		llama.h
+13 −1		scripts/sync-ggml-am.sh
+1 −1		scripts/sync-ggml.last
+1 −1		tests/test-backend-ops.cpp

0 comments on commit `46f3740`

Please sign in to comment.