Skip to content

ggml-cpu: arm64: q4_K repack gemm and gemv implementations (i8mm) #16739

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

Open
wants to merge 12 commits into
base: master
Choose a base branch
from
+410 −2
Open

ggml-cpu: arm64: q4_K repack gemm and gemv implementations (i8mm) #16739

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
12 commits
Select commit Hold shift + click to select a range
1f7f498
Enabled q4_K_8x8_q8_K path on ARM
Alcpz Oct 13, 2025
4e5be2c
wip: I8mm qs multiplication, pending bias
Alcpz Oct 17, 2025
f9e1527
cpu : arm : REPACK gemm q4_K8x8 implementation
Alcpz Oct 21, 2025
28e30c2
Guard gemm with proper features, improved superblock scale and min calc
Alcpz Oct 22, 2025
0b1fec6
cpu: arm: Implemented REPACK gemv for Q4_K
Alcpz Oct 22, 2025
c14e3e4
Removed completed TODO
Alcpz Oct 22, 2025
0b45665
Fixed missing guards when selecting optimal repack type for Q4_K
Alcpz Oct 23, 2025
f678c83
Fixed macro guard for gemv
Alcpz Oct 23, 2025
ef01952
Fixed wrong comment in GEMV
Alcpz Oct 23, 2025
c4f1358
Fixed warning for unused variable
Alcpz Oct 23, 2025
5bbed90
vdotq_s32 -> ggml_vdotq_s32
Alcpz Oct 27, 2025
7081eda
Clang-format issues
Alcpz Oct 28, 2025
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
2 changes: 0 additions & 2 deletions ggml/src/ggml-cpu/arch-fallback.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -51,10 +51,8 @@
#elif defined(__aarch64__) || defined(__arm__) || defined(_M_ARM) || defined(_M_ARM64)
// repack.cpp
#define ggml_quantize_mat_q8_K_4x8_generic ggml_quantize_mat_q8_K_4x8
#define ggml_gemv_q4_K_8x8_q8_K_generic ggml_gemv_q4_K_8x8_q8_K
#define ggml_gemv_iq4_nl_8x8_q8_0_generic ggml_gemv_iq4_nl_8x8_q8_0
#define ggml_gemv_q2_K_8x8_q8_K_generic ggml_gemv_q2_K_8x8_q8_K
#define ggml_gemm_q4_K_8x8_q8_K_generic ggml_gemm_q4_K_8x8_q8_K
#define ggml_gemm_iq4_nl_8x8_q8_0_generic ggml_gemm_iq4_nl_8x8_q8_0
#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)
Expand Down
Loading
Loading