You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
I am trying to run "make" on an odroid sbc and get following error:
`I llama.cpp build info:
I UNAME_S: Linux
I UNAME_P: unknown
I UNAME_M: armv7l
I CFLAGS: -I. -O3 -DNDEBUG -std=c11 -fPIC -pthread -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access -funsafe-math-optimizations
I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -pthread
I LDFLAGS:
I CC: cc (Debian 10.2.1-6) 10.2.1 20210110
I CXX: g++ (Debian 10.2.1-6) 10.2.1 20210110
cc -I. -O3 -DNDEBUG -std=c11 -fPIC -pthread -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access -funsafe-math-optimizations -c ggml.c -o ggml.o
ggml.c: In function ‘ggml_vec_mad_q4_0’:
ggml.c:2049:35: warning: implicit declaration of function ‘vzip1_s8’; did you mean ‘vzipq_s8’? [-Wimplicit-function-declaration]
2049 | const int8x8_t vxlt = vzip1_s8(vxls, vxhs);
| ^~~~~~~~
| vzipq_s8
ggml.c:2049:35: error: incompatible types when initializing type ‘int8x8_t’ using type ‘int’
ggml.c:2050:35: warning: implicit declaration of function ‘vzip2_s8’; did you mean ‘vzipq_s8’? [-Wimplicit-function-declaration]
2050 | const int8x8_t vxht = vzip2_s8(vxls, vxhs);
| ^~~~~~~~
| vzipq_s8
ggml.c:2050:35: error: incompatible types when initializing type ‘int8x8_t’ using type ‘int’
make: *** [Makefile:222: ggml.o] Error 1
`
Also trying to run the docker image causes following:
Unable to find image 'ghcr.io/ggerganov/llama.cpp:light' locally
light: Pulling from ggerganov/llama.cpp
docker: no matching manifest for linux/arm/v7 in the manifest list entries.
See 'docker run --help'.
The text was updated successfully, but these errors were encountered:
I am trying to run "make" on an odroid sbc and get following error:
`I llama.cpp build info:
I UNAME_S: Linux
I UNAME_P: unknown
I UNAME_M: armv7l
I CFLAGS: -I. -O3 -DNDEBUG -std=c11 -fPIC -pthread -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access -funsafe-math-optimizations
I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -pthread
I LDFLAGS:
I CC: cc (Debian 10.2.1-6) 10.2.1 20210110
I CXX: g++ (Debian 10.2.1-6) 10.2.1 20210110
cc -I. -O3 -DNDEBUG -std=c11 -fPIC -pthread -mfpu=neon-fp-armv8 -mfp16-format=ieee -mno-unaligned-access -funsafe-math-optimizations -c ggml.c -o ggml.o
ggml.c: In function ‘ggml_vec_mad_q4_0’:
ggml.c:2049:35: warning: implicit declaration of function ‘vzip1_s8’; did you mean ‘vzipq_s8’? [-Wimplicit-function-declaration]
2049 | const int8x8_t vxlt = vzip1_s8(vxls, vxhs);
| ^~~~~~~~
| vzipq_s8
ggml.c:2049:35: error: incompatible types when initializing type ‘int8x8_t’ using type ‘int’
ggml.c:2050:35: warning: implicit declaration of function ‘vzip2_s8’; did you mean ‘vzipq_s8’? [-Wimplicit-function-declaration]
2050 | const int8x8_t vxht = vzip2_s8(vxls, vxhs);
| ^~~~~~~~
| vzipq_s8
ggml.c:2050:35: error: incompatible types when initializing type ‘int8x8_t’ using type ‘int’
make: *** [Makefile:222: ggml.o] Error 1
`
Also trying to run the docker image causes following:
Unable to find image 'ghcr.io/ggerganov/llama.cpp:light' locally
light: Pulling from ggerganov/llama.cpp
docker: no matching manifest for linux/arm/v7 in the manifest list entries.
See 'docker run --help'.
The text was updated successfully, but these errors were encountered: