Skip to content

fix crash on non-AVX systems dynamically loading GGML CPU backends #11780

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
Feb 13, 2025
Merged

fix crash on non-AVX systems dynamically loading GGML CPU backends #11780

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
17 changes: 9 additions & 8 deletions ggml/src/ggml-cpu/llamafile/sgemm.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -280,14 +280,6 @@ template <> inline __m256bh load(const float *p) {
}
#endif

////////////////////////////////////////////////////////////////////////////////////////////////////
// CONSTANTS

#if defined(__AVX__) || defined(__AVX2__) || defined(__AVX512F__)
static const int8_t kvalues_iq4nl[16] = {-127, -104, -83, -65, -49, -35, -22, -10, 1, 13, 25, 38, 53, 69, 89, 113};
static const __m128i iq4nlt = _mm_loadu_si128((const __m128i *) kvalues_iq4nl);
#endif

////////////////////////////////////////////////////////////////////////////////////////////////////
// FLOATING POINT MATRIX MULTIPLICATION

Expand Down Expand Up @@ -614,6 +606,14 @@ class tinyBLAS_Q0_AVX {
TC *C, int64_t ldc,
int ith, int nth)
: A(A), B(B), C(C), k(k), lda(lda), ldb(ldb), ldc(ldc), ith(ith), nth(nth) {
const int8_t kvalues_iq4nl[16] = {
-127, -104, -83, -65,
-49, -35, -22, -10,
1, 13, 25, 38,
53, 69, 89, 113
};

iq4nlt = _mm_loadu_si128((const __m128i *)kvalues_iq4nl);
}

void matmul(int64_t m, int64_t n) {
Expand Down Expand Up @@ -1038,6 +1038,7 @@ class tinyBLAS_Q0_AVX {
const int64_t ldc;
const int ith;
const int nth;
__m128i iq4nlt;
};
#endif // __AVX__

Expand Down
Loading