search

ggerganov / llama.cpp

LLM inference in C/C++
MIT License
67.49k stars 9.69k forks source link

LLAMA_BUILD_SERVER=1 make command execution error #2096

Closed stoneLee81 closed 1 year ago

stoneLee81 commented 1 year ago

I execute the LLAMA_BUILD_SERVER=1 make command in the root directory of the llama.cpp project， But compilation fails with below error

I llama.cpp build info: I UNAME_S: Darwin I UNAME_P: arm I UNAME_M: arm64 I CFLAGS: -I. -O3 -std=c11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wdouble-promotion -Wshadow -Wstrict-prototypes -Wpointer-arith -pthread -DGGML_USE_K_QUANTS -DGGML_USE_ACCELERATE I CXXFLAGS: -I. -I./examples -O3 -std=c++11 -fPIC -DNDEBUG -Wall -Wextra -Wpedantic -Wcast-qual -Wno-unused-function -Wno-multichar -pthread -DGGML_USE_K_QUANTS I LDFLAGS: -framework Accelerate I CC: Apple clang version 14.0.3 (clang-1403.0.22.14.1) I CXX: Apple clang version 14.0.3 (clang-1403.0.22.14.1)

make: *** No rule to make target private', needed byserver'. Stop.

I don't know what went wrong, causing the failure

os: Ventura 13.4.1 m1max gcc: Apple clang version 14.0.3 (clang-1403.0.22.14.1)

Green-Sky commented 1 year ago

try to install gmake via brew, or use the cmake project

SlyEcho commented 1 year ago

It's caused by Apple using a very old GNU Make version.

SlyEcho commented 1 year ago

@Green-Sky, I planned to fix this, I will make a quick PR, alright?