tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-08-18 22:20:16 -04:00
Code Issues Packages Projects Releases Wiki Activity

Speedup the AVX-512 implementation of ggml_vec_dot_q4_0() (#933)

Browse Source
This commit is contained in:
Ivan Komarov
2023-04-17 15:10:57 +02:00
committed by GitHub
parent 47f61aaa5f
commit f266259ad9
4 changed files with 235 additions and 44 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
ggml.h
View File

@@ -808,6 +808,8 @@ size_t ggml_quantize_q4_1(const float * src, void * dst, int n, int k, int64_t *
int ggml_cpu_has_avx(void);
int ggml_cpu_has_avx2(void);
int ggml_cpu_has_avx512(void);
int ggml_cpu_has_avx512_vbmi(void);
int ggml_cpu_has_avx512_vnni(void);
int ggml_cpu_has_fma(void);
int ggml_cpu_has_neon(void);
int ggml_cpu_has_arm_fma(void);