llama.cpp
llama.cpp copied to clipboard
Published
20 hours ago •
ggml-org
ggml-org
making on linuxmint 21
im running on bare metal nothing emulated
littlemac@littlemac:~$` git clone https://github.com/ggerganov/llama.cpp
Cloning into 'llama.cpp'...
remote: Enumerating objects: 283, done.
remote: Counting objects: 100% (283/283), done.
remote: Compressing objects: 100% (113/113), done.
remote: Total 283 (delta 180), reused 255 (delta 164), pack-reused 0
Receiving objects: 100% (283/283), 158.38 KiB | 609.00 KiB/s, done.
Resolving deltas: 100% (180/180), done.
cd littlemac@littlemac:~$ cd llama.cpp/
littlemac@littlemac:~/llama.cpp$ make
I llama.cpp build info:
I UNAME_S: Linux
I UNAME_P: x86_64
I UNAME_M: x86_64
I CFLAGS: -I. -O3 -DNDEBUG -std=c11 -fPIC -pthread -mavx -msse3
I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -pthread
I LDFLAGS:
I CC: cc (Ubuntu 11.3.0-1ubuntu1~22.04) 11.3.0
I CXX: g++ (Ubuntu 11.3.0-1ubuntu1~22.04) 11.3.0
cc -I. -O3 -DNDEBUG -std=c11 -fPIC -pthread -mavx -msse3 -c ggml.c -o ggml.o
In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:101,
from ggml.c:155:
ggml.c: In function ‘ggml_vec_dot_f16’:
/usr/lib/gcc/x86_64-linux-gnu/11/include/f16cintrin.h:52:1: error: inlining failed in call to ‘always_inline’ ‘_mm256_cvtph_ps’: target specific option mismatch
52 | _mm256_cvtph_ps (__m128i __A)
| ^~~~~~~~~~~~~~~
ggml.c:911:33: note: called from here
911 | #define GGML_F32Cx8_LOAD(x) _mm256_cvtph_ps(_mm_loadu_si128((__m128i *)(x)))
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
ggml.c:921:37: note: in expansion of macro ‘GGML_F32Cx8_LOAD’
921 | #define GGML_F16_VEC_LOAD(p, i) GGML_F32Cx8_LOAD(p)
| ^~~~~~~~~~~~~~~~
ggml.c:1274:21: note: in expansion of macro ‘GGML_F16_VEC_LOAD’
1274 | ay[j] = GGML_F16_VEC_LOAD(y + i + j*GGML_F16_EPR, j);
| ^~~~~~~~~~~~~~~~~
In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:101,
from ggml.c:155:
/usr/lib/gcc/x86_64-linux-gnu/11/include/f16cintrin.h:52:1: error: inlining failed in call to ‘always_inline’ ‘_mm256_cvtph_ps’: target specific option mismatch
52 | _mm256_cvtph_ps (__m128i __A)
| ^~~~~~~~~~~~~~~
ggml.c:911:33: note: called from here
911 | #define GGML_F32Cx8_LOAD(x) _mm256_cvtph_ps(_mm_loadu_si128((__m128i *)(x)))
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
ggml.c:921:37: note: in expansion of macro ‘GGML_F32Cx8_LOAD’
921 | #define GGML_F16_VEC_LOAD(p, i) GGML_F32Cx8_LOAD(p)
| ^~~~~~~~~~~~~~~~
ggml.c:1273:21: note: in expansion of macro ‘GGML_F16_VEC_LOAD’
1273 | ax[j] = GGML_F16_VEC_LOAD(x + i + j*GGML_F16_EPR, j);
| ^~~~~~~~~~~~~~~~~
In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:101,
from ggml.c:155:
/usr/lib/gcc/x86_64-linux-gnu/11/include/f16cintrin.h:52:1: error: inlining failed in call to ‘always_inline’ ‘_mm256_cvtph_ps’: target specific option mismatch
52 | _mm256_cvtph_ps (__m128i __A)
| ^~~~~~~~~~~~~~~
ggml.c:911:33: note: called from here
911 | #define GGML_F32Cx8_LOAD(x) _mm256_cvtph_ps(_mm_loadu_si128((__m128i *)(x)))
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
ggml.c:921:37: note: in expansion of macro ‘GGML_F32Cx8_LOAD’
921 | #define GGML_F16_VEC_LOAD(p, i) GGML_F32Cx8_LOAD(p)
| ^~~~~~~~~~~~~~~~
ggml.c:1273:21: note: in expansion of macro ‘GGML_F16_VEC_LOAD’
1273 | ax[j] = GGML_F16_VEC_LOAD(x + i + j*GGML_F16_EPR, j);
| ^~~~~~~~~~~~~~~~~
In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:101,
from ggml.c:155:
/usr/lib/gcc/x86_64-linux-gnu/11/include/f16cintrin.h:52:1: error: inlining failed in call to ‘always_inline’ ‘_mm256_cvtph_ps’: target specific option mismatch
52 | _mm256_cvtph_ps (__m128i __A)
| ^~~~~~~~~~~~~~~
ggml.c:911:33: note: called from here
911 | #define GGML_F32Cx8_LOAD(x) _mm256_cvtph_ps(_mm_loadu_si128((__m128i *)(x)))
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
ggml.c:921:37: note: in expansion of macro ‘GGML_F32Cx8_LOAD’
921 | #define GGML_F16_VEC_LOAD(p, i) GGML_F32Cx8_LOAD(p)
| ^~~~~~~~~~~~~~~~
ggml.c:1274:21: note: in expansion of macro ‘GGML_F16_VEC_LOAD’
1274 | ay[j] = GGML_F16_VEC_LOAD(y + i + j*GGML_F16_EPR, j);
| ^~~~~~~~~~~~~~~~~
In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:101,
from ggml.c:155:
/usr/lib/gcc/x86_64-linux-gnu/11/include/f16cintrin.h:52:1: error: inlining failed in call to ‘always_inline’ ‘_mm256_cvtph_ps’: target specific option mismatch
52 | _mm256_cvtph_ps (__m128i __A)
| ^~~~~~~~~~~~~~~
ggml.c:911:33: note: called from here
911 | #define GGML_F32Cx8_LOAD(x) _mm256_cvtph_ps(_mm_loadu_si128((__m128i *)(x)))
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
ggml.c:921:37: note: in expansion of macro ‘GGML_F32Cx8_LOAD’
921 | #define GGML_F16_VEC_LOAD(p, i) GGML_F32Cx8_LOAD(p)
| ^~~~~~~~~~~~~~~~
ggml.c:1273:21: note: in expansion of macro ‘GGML_F16_VEC_LOAD’
1273 | ax[j] = GGML_F16_VEC_LOAD(x + i + j*GGML_F16_EPR, j);
| ^~~~~~~~~~~~~~~~~
In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:101,
from ggml.c:155:
/usr/lib/gcc/x86_64-linux-gnu/11/include/f16cintrin.h:52:1: error: inlining failed in call to ‘always_inline’ ‘_mm256_cvtph_ps’: target specific option mismatch
52 | _mm256_cvtph_ps (__m128i __A)
| ^~~~~~~~~~~~~~~
ggml.c:911:33: note: called from here
911 | #define GGML_F32Cx8_LOAD(x) _mm256_cvtph_ps(_mm_loadu_si128((__m128i *)(x)))
| ^~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
ggml.c:921:37: note: in expansion of macro ‘GGML_F32Cx8_LOAD’
921 | #define GGML_F16_VEC_LOAD(p, i) GGML_F32Cx8_LOAD(p)
| ^~~~~~~~~~~~~~~~
ggml.c:1274:21: note: in expansion of macro ‘GGML_F16_VEC_LOAD’
1274 | ay[j] = GGML_F16_VEC_LOAD(y + i + j*GGML_F16_EPR, j);
| ^~~~~~~~~~~~~~~~~
make: *** [Makefile:186: ggml.o] Error 1
littlemac@littlemac:~/llama.cpp$ cpu-x -D
Your CPU socket is not present in the database ==> Intel(R) Core(TM) i5-2500K CPU @ 3.30GHz, codename: Sandy Bridge (Core i5)
CPU-X:core.c:1637: failed to retrieve CPU voltage (fallback mode)
>>>>>>>>>> CPU <<<<<<<<<<
***** Processor *****
Vendor: Intel
Code Name: Sandy Bridge (Core i5)
Package:
Technology: 32 nm
Voltage:
Specification: Intel(R) Core(TM) i5-2500K CPU @ 3.30GHz
Family: 0x6
Ext. Family: 0x6
Model: 0xA
Ext. Model: 0x2A
Temp.: 28.00°C
Stepping: 7
Instructions: MMX, SSE(1, 2, 3, 3S, 4.1, 4.2), AVX(1), AES, CLMUL, VT-x, x86-64
***** Clocks *****
Core Speed: 3679 MHz
Multiplier:
Bus Speed:
Usage: 15.22 %
***** Cache *****
L1 Data: 4 x 32 kB, 8-way
L1 Inst.: 4 x 32 kB, 8-way
Level 2: 4 x 256 kB, 8-way
Level 3: 6 MB, 12-way
***** * *****
Socket(s): 1
Core(s): 4
Thread(s): 4
>>>>>>>>>> Caches <<<<<<<<<<
***** L1 Cache *****
Size: 4 x 32 kB, 8-way associative, 64-bytes line size
Speed: 110315.60 MB/s
***** L2 Cache *****
Size: 4 x 256 kB, 8-way associative, 64-bytes line size
Speed: 53894.20 MB/s
***** L3 Cache *****
Size: 6 MB, 12-way associative, 64-bytes line size
Speed: 33268.30 MB/s
>>>>>>>>>> Motherboard <<<<<<<<<<
***** Motherboard *****
Manufacturer: MSI
Model: Z77A-G43 (MS-7758)
Revision: 1.0
***** BIOS *****
Brand: American Megatrends Inc.
Version: V2.7
Date: 10/24/2012
ROM Size:
***** Chipset *****
Vendor: Intel Corporation
Model: Z77 Express Chipset LPC Controller
>>>>>>>>>> Memory <<<<<<<<<<
>>>>>>>>>> System <<<<<<<<<<
***** Operating System *****
Kernel: Linux 5.15.0-67-generic
Distribution: Linux Mint 21.1
Hostname: littlemac
Uptime: 0 days, 0 hours, 12 minutes, 29 seconds
Compiler: cc (Ubuntu 11.3.0-1ubuntu1~22.04) 11.3.0
***** Memory *****
Used: 2.17 GiB / 7.71 GiB
Buffers: 0.12 GiB / 7.71 GiB
Cached: 3.86 GiB / 7.71 GiB
Free: 1.55 GiB / 7.71 GiB
Swap: 0.00 GiB / 5.85 GiB
>>>>>>>>>> Graphics <<<<<<<<<<
***** Card 0 *****
Vendor: NVIDIA
Driver: nvidia
UMD Version: NVIDIA 515.86.01
Model: GM206 [GeForce GTX 960]
DeviceID: 0x1401:0xA1
Interface:
Temperature: 34.00°C
Usage: 2%
Core Voltage:
Power Avg: 25.00 W
GPU clock: 1126 MHz
Memory clock: 3004 MHz
Memory Used: 342 MiB / 2048 MiB
Presumably fixed by #563, please re-open if it's still an issue with a recent revision.
