Skip to content

Much faster prompt processing for k-quants (ARM_NEON) #552

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

Merged
merged 12 commits into from
Jun 24, 2025
Merged

Much faster prompt processing for k-quants (ARM_NEON) #552

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
edb5f9c
iq2_xxs
Jun 23, 2025
8b33186
iq2_xs
Jun 23, 2025
c52f589
iq2_s
Jun 23, 2025
2696567
iq3_xxs
Jun 23, 2025
548a5f3
iq3_s
Jun 23, 2025
6818e14
q2_k
Jun 23, 2025
52ad57b
q3_K
Jun 23, 2025
78d531c
q6_k
Jun 24, 2025
d1b4b34
q4_k
Jun 24, 2025
915a4a3
q5_k
Jun 24, 2025
c3c60c3
iq4_xs
Jun 24, 2025
e18b10b
Merge remote-tracking branch 'origin/main' into ik/gemm_neon_kquants
Jun 24, 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
6 changes: 3 additions & 3 deletions ggml/src/ggml.c
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -979,7 +979,7 @@ static const ggml_type_traits_t type_traits[GGML_TYPE_COUNT] = {
#ifdef __AVX2__
.vec_dot_type = GGML_TYPE_Q8_2_X4,
#else
.vec_dot_type = GGML_TYPE_Q8_K,
.vec_dot_type = GGML_TYPE_Q8_1_X4,
#endif
.nrows = 1,
.row_meta_size = 0,
Expand Down Expand Up @@ -1009,7 +1009,7 @@ static const ggml_type_traits_t type_traits[GGML_TYPE_COUNT] = {
#ifdef __AVX2__
.vec_dot_type = GGML_TYPE_Q8_2_X4,
#else
.vec_dot_type = GGML_TYPE_Q8_K,
.vec_dot_type = GGML_TYPE_Q8_1_X4,
#endif
.nrows = 1,
.row_meta_size = 0,
Expand Down Expand Up @@ -1039,7 +1039,7 @@ static const ggml_type_traits_t type_traits[GGML_TYPE_COUNT] = {
#ifdef __AVX2__
.vec_dot_type = GGML_TYPE_Q8_2_X4,
#else
.vec_dot_type = GGML_TYPE_Q8_K,
.vec_dot_type = GGML_TYPE_Q8_0_X4,
#endif
// .vec_dot_type = GGML_TYPE_Q8_K,
.nrows = 1,
Expand Down
Loading