ggerganov / whisper.cpp

Port of OpenAI's Whisper model in C/C++
MIT License
35.5k stars 3.61k forks source link

The project cannot be run, an error was reported when running the make stream command #991

Open liu199811 opened 1 year ago

liu199811 commented 1 year ago

In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:99, from ggml.c:189: ggml.c: In function ‘ggml_vec_dot_q4_0_q8_0’: /usr/lib/gcc/x86_64-linux-gnu/11/include/fmaintrin.h:63:1: error: inlining failed in call to ‘always_inline’ ‘_mm256_fmadd_ps’: target specific option mismatch 63 | _mm256_fmadd_ps (m256 A, m256 B, m256 C) | ^~~~~~~ ggml.c:2262:15: note: called from here

liu199811 commented 1 year ago

1

liu199811 commented 1 year ago

1

Bessonov commented 1 year ago

I get the same error. Tried master, 1.4.2 and every tag down to 1.1.1:

$ make -j 8
I whisper.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 -mavx2 -msse3
I CXXFLAGS: -I. -I./examples -O3 -DNDEBUG -std=c++11 -fPIC -pthread
I LDFLAGS:  
I CC:       cc (Ubuntu 11.3.0-1ubuntu1~22.04.1) 11.3.0
I CXX:      g++ (Ubuntu 11.3.0-1ubuntu1~22.04.1) 11.3.0

cc  -I.              -O3 -DNDEBUG -std=c11   -fPIC -pthread -mavx2 -msse3   -c ggml.c -o ggml.o
In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:99,
                 from ggml.c:189:
ggml.c: In function ‘ggml_vec_dot_q4_0_q8_0’:
/usr/lib/gcc/x86_64-linux-gnu/11/include/fmaintrin.h:63:1: error: inlining failed in call to ‘always_inline’ ‘_mm256_fmadd_ps’: target specific option mismatch
   63 | _mm256_fmadd_ps (__m256 __A, __m256 __B, __m256 __C)
      | ^~~~~~~~~~~~~~~
ggml.c:2166:15: note: called from here
 2166 |         acc = _mm256_fmadd_ps( d, q, acc );
      |               ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:99,
                 from ggml.c:189:
/usr/lib/gcc/x86_64-linux-gnu/11/include/fmaintrin.h:63:1: error: inlining failed in call to ‘always_inline’ ‘_mm256_fmadd_ps’: target specific option mismatch
   63 | _mm256_fmadd_ps (__m256 __A, __m256 __B, __m256 __C)
      | ^~~~~~~~~~~~~~~
ggml.c:2166:15: note: called from here
 2166 |         acc = _mm256_fmadd_ps( d, q, acc );
      |               ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:99,
                 from ggml.c:189:
/usr/lib/gcc/x86_64-linux-gnu/11/include/fmaintrin.h:63:1: error: inlining failed in call to ‘always_inline’ ‘_mm256_fmadd_ps’: target specific option mismatch
   63 | _mm256_fmadd_ps (__m256 __A, __m256 __B, __m256 __C)
      | ^~~~~~~~~~~~~~~
ggml.c:2166:15: note: called from here
 2166 |         acc = _mm256_fmadd_ps( d, q, acc );
      |               ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
In file included from /usr/lib/gcc/x86_64-linux-gnu/11/include/immintrin.h:99,
                 from ggml.c:189:
/usr/lib/gcc/x86_64-linux-gnu/11/include/fmaintrin.h:63:1: error: inlining failed in call to ‘always_inline’ ‘_mm256_fmadd_ps’: target specific option mismatch
   63 | _mm256_fmadd_ps (__m256 __A, __m256 __B, __m256 __C)
      | ^~~~~~~~~~~~~~~
ggml.c:2166:15: note: called from here
 2166 |         acc = _mm256_fmadd_ps( d, q, acc );
      |               ^~~~~~~~~~~~~~~~~~~~~~~~~~~~
make: *** [Makefile:234: ggml.o] Error 1
Bessonov commented 1 year ago

Additional info:

$ cat /proc/cpuinfo 
processor   : 0
vendor_id   : GenuineIntel
cpu family  : 6
model       : 154
model name  : 12th Gen Intel(R) Core(TM) i9-12900H
stepping    : 3
cpu MHz     : 2918.398
cache size  : 24576 KB
physical id : 0
siblings    : 24
core id     : 0
cpu cores   : 24
apicid      : 0
initial apicid  : 0
fpu     : yes
fpu_exception   : yes
cpuid level : 22
wp      : yes
flags       : fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush mmx fxsr sse sse2 ht syscall nx rdtscp lm constant_tsc rep_good nopl xtopology nonstop_tsc cpuid tsc_known_freq pni pclmulqdq vmx ssse3 cx16 pcid sse4_1 sse4_2 x2apic movbe popcnt aes xsave avx rdrand hypervisor lahf_lm abm 3dnowprefetch invpcid_single tpr_shadow vnmi flexpriority vpid fsgsbase avx2 invpcid rdseed clflushopt md_clear flush_l1d arch_capabilities
vmx flags   : vnmi flexpriority tsc_offset vtpr vapic
bugs        : spectre_v1 spectre_v2 spec_store_bypass swapgs
bogomips    : 5836.79
clflush size    : 64
cache_alignment : 64
address sizes   : 46 bits physical, 48 bits virtual
power management:
[...]

Running in a vagrant box.