Lumpiasty/llama.cpp
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ggml-cpu: add AVX2 optimization for nvfp4 dot product and use UE4M3 LUT (#23961)

Browse Source
This commit is contained in:
ragz4125
2026-07-01 15:31:20 +08:00
committed by GitHub
parent 9d88e7cedd
commit 6dbc1174b8
5 changed files with 164 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files
ggml/src/ggml-cpu/arch-fallback.h
-1
View File
@@ -82,7 +82,6 @@
#define ggml_gemm_q2_K_8x8_q8_K_generic ggml_gemm_q2_K_8x8_q8_K
#elif defined(__x86_64__) || defined(__i386__) || defined(_M_IX86) || defined(_M_X64)
// quants.c
#define ggml_vec_dot_nvfp4_q8_0_generic ggml_vec_dot_nvfp4_q8_0
// repack.cpp
#define ggml_quantize_mat_q8_0_4x4_generic ggml_quantize_mat_q8_0_4x4
#define ggml_quantize_mat_q8_K_4x4_generic ggml_quantize_mat_q8_K_4x4