happyz
/
llama.cpp
mirror of https://github.com/ggerganov/llama.cpp.git
1
0
Fork 0
Code Issues Packages Projects Releases Wiki Activity

fix x86 call due to prototype change

This commit is contained in:
hongyang 2025-12-19 14:41:15 +08:00
parent 126ce2c9e4
commit 41780fe07e
1 changed files with 3 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

5
ggml/src/ggml-cpu/arch/x86/repack.cpp
View File

@ -287,9 +287,10 @@ void ggml_quantize_mat_q8_0_4x8(const float * GGML_RESTRICT x, void * GGML_RESTR
#endif
}
void ggml_quantize_mat_q8_K_4x8(const float * GGML_RESTRICT x, void * GGML_RESTRICT vy, int64_t k) {
void ggml_quantize_mat_q8_K_4x8(const float * GGML_RESTRICT x, void * GGML_RESTRICT vy, int64_t k, int64_t nc) {
assert(QK_K == 256);
assert(k % QK_K == 0);
UNUSED(nc);
const int nb = k / QK_K;
block_q8_Kx4 * GGML_RESTRICT y = (block_q8_Kx4 *) vy;
@ -507,7 +508,7 @@ void ggml_quantize_mat_q8_K_4x8(const float * GGML_RESTRICT x, void * GGML_RESTR
#else
UNUSED(nb);
UNUSED(y);
ggml_quantize_mat_q8_K_4x8_generic(x, vy, k);
ggml_quantize_mat_q8_K_4x8_generic(x, vy, k, nc);
#endif
}