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

Will this fix ROCm?

Browse source
This commit is contained in:
Iwan Kawrakow 2024-02-23 16:24:52 +02:00
parent cbd950b220
commit e1b8efb9ac
1 changed files with 1 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml-cuda.cu
View file

@ -172,7 +172,7 @@
#endif #endif
typedef int8_t int8x4_t __attribute__((ext_vector_type(4))); typedef int8_t int8x4_t __attribute__((ext_vector_type(4)));
typedef uint8_t int8x4_t __attribute__((ext_vector_type(4))); typedef uint8_t uint8x4_t __attribute__((ext_vector_type(4)));
static __device__ __forceinline__ int __vsubss4(const int a, const int b) { static __device__ __forceinline__ int __vsubss4(const int a, const int b) {
const int8x4_t va = reinterpret_cast<const int8x4_t&>(a); const int8x4_t va = reinterpret_cast<const int8x4_t&>(a);
const int8x4_t vb = reinterpret_cast<const int8x4_t&>(b); const int8x4_t vb = reinterpret_cast<const int8x4_t&>(b);