vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Do not include arm_neon.h when compiling CUDA code (ggml/1028)

Browse source
This commit is contained in:
Frankie Robertson 2024-11-26 15:50:26 +02:00 • committed by Georgi Gerganov
parent c31ed2abfc
commit 9150f8fef9
No known key found for this signature in database
GPG key ID: BF970631944C16B7
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml/src/ggml-impl.h
View file

@ -14,7 +14,7 @@
#include <arm_sve.h> #include <arm_sve.h>
#endif // __ARM_FEATURE_SVE #endif // __ARM_FEATURE_SVE
#if defined(__ARM_NEON) #if defined(__ARM_NEON) && !defined(__CUDACC__)
// if YCM cannot find <arm_neon.h>, make a symbolic link to it, for example: // if YCM cannot find <arm_neon.h>, make a symbolic link to it, for example:
// //
// $ ln -sfn /Library/Developer/CommandLineTools/usr/lib/clang/13.1.6/include/arm_neon.h ./src/ // $ ln -sfn /Library/Developer/CommandLineTools/usr/lib/clang/13.1.6/include/arm_neon.h ./src/