Skip to content

ggml-cpu: add RVV repack GEMM and GEMV for Q3_K, Q6_K #12

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
taimur-10x wants to merge 13 commits into
base: master
Choose a base branch
from
Open

ggml-cpu: add RVV repack GEMM and GEMV for Q3_K, Q6_K #12

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
ff49890
ggml-cpu: add rvv ggml_quantize_mat_4x8 for q8_0
taimur-10x Dec 15, 2025
9bd6c9e
ggml-cpu: add rvv repacking for iq4_nl
taimur-10x Dec 15, 2025
dbd1667
ggml-cpu: add generic impl for iq4_nl gemm/gemv
taimur-10x Dec 30, 2025
d9fbb69
ggml-cpu: add rvv repacking for q8_0
taimur-10x Dec 30, 2025
6502d03
ggml-cpu: refactor; add rvv repacking for q4_0, q4_K
taimur-10x Jan 2, 2026
981bbc5
ggml-cpu: refactor; add rvv repacking for q2_K
taimur-10x Jan 12, 2026
a037b85
ggml-cpu: refactor rvv repack
taimur-10x Mar 4, 2026
85c6e8f
ggml-cpu: extend rvv gemm, gemv to other vlens
taimur-10x Feb 2, 2026
d646c0d
ggml-cpu: refactor; add rvv repacking for q6_K
taimur-10x Feb 6, 2026
90c9244
ggml-cpu: refactor; add rvv repacking for q5_K
taimur-10x Feb 11, 2026
6df5cef
ggml-cpu: refactor; add rvv repacking for q3_K
RehanQasim-dev Feb 18, 2026
c4808af
ggml-cpu: refactor; add rvv repacking for q5_K
taimur-10x Feb 19, 2026
053cb1c
ggml-cpu: refactor; add rvv repacking for mxfp4
taimur-10x Mar 4, 2026
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
3 changes: 2 additions & 1 deletion ggml/src/ggml-cpu/arch-fallback.h
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -202,8 +202,9 @@
#define ggml_vec_dot_iq4_xs_q8_K_generic ggml_vec_dot_iq4_xs_q8_K
#define ggml_vec_dot_mxfp4_q8_0_generic ggml_vec_dot_mxfp4_q8_0
// repack.cpp
#define ggml_quantize_mat_q8_0_4x1_generic ggml_quantize_mat_q8_0_4x1
#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
#define ggml_quantize_mat_q8_K_4x1_generic ggml_quantize_mat_q8_K_4x1
#define ggml_quantize_mat_q8_K_4x4_generic ggml_quantize_mat_q8_K_4x4
#define ggml_quantize_mat_q8_K_4x8_generic ggml_quantize_mat_q8_K_4x8
#define ggml_gemv_q4_0_4x4_q8_0_generic ggml_gemv_q4_0_4x4_q8_0
Expand Down
Loading
Loading