CS348Project/llama.cpp
5
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-10-28 08:31:25 +00:00
Code Issues Packages Projects Releases Wiki Activity

ggml-cpu: add mxfp4 VSX intrinsics for Power9+ (ppc64le) hardware (#15385)

Browse Source 
* Added VSX intrinsics for Power9+ systems

Signed-off-by: mgiessing <marvin.giessing@gmail.com>

* Manual unrolling for minor perf improvement

Signed-off-by: mgiessing <marvin.giessing@gmail.com>

* Update ggml/src/ggml-cpu/arch/powerpc/quants.c

Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>

---------

Signed-off-by: mgiessing <marvin.giessing@gmail.com>
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Marvin Gießing
2025-08-19 10:54:31 +02:00
committed by GitHub
parent e9288e8869
commit 6424594c56
2 changed files with 66 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

1
ggml/src/ggml-cpu/arch-fallback.h
View File

@@ -73,7 +73,6 @@
#define ggml_vec_dot_tq1_0_q8_K_generic ggml_vec_dot_tq1_0_q8_K
#define ggml_vec_dot_tq2_0_q8_K_generic ggml_vec_dot_tq2_0_q8_K
#define ggml_vec_dot_iq1_m_q8_K_generic ggml_vec_dot_iq1_m_q8_K
#define ggml_vec_dot_mxfp4_q8_0_generic ggml_vec_dot_mxfp4_q8_0
// repack.cpp
#define ggml_quantize_mat_q8_0_4x4_generic ggml_quantize_mat_q8_0_4x4
#define ggml_quantize_mat_q8_0_4x8_generic ggml_quantize_mat_q8_0_4x8