Skip to content

sync : ggml #17988

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
ggerganov merged 4 commits into from
Dec 14, 2025
+7 −1
Merged

sync : ggml #17988

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
14bd4d3
cmake : set `CMAKE_RUNTIME_OUTPUT_DIRECTORY` for non standalone build…
HerrCai0907 Dec 12, 2025
c32f474
ggml : arm repack fix build (whisper/0)
ggerganov Dec 13, 2025
5f9b1cc
sync : ggml
ggerganov Dec 13, 2025
de3d7cc
ggml : arm repack fix build
ggerganov Dec 13, 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
4 changes: 4 additions & 0 deletions ggml/CMakeLists.txt
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,10 @@ if (CMAKE_SOURCE_DIR STREQUAL CMAKE_CURRENT_SOURCE_DIR)
# TODO
else()
set(GGML_STANDALONE OFF)

if (NOT CMAKE_RUNTIME_OUTPUT_DIRECTORY)
set(CMAKE_RUNTIME_OUTPUT_DIRECTORY ${CMAKE_BINARY_DIR}/bin)
endif()
endif()

if (EMSCRIPTEN)
Expand Down
2 changes: 2 additions & 0 deletions ggml/src/ggml-cpu/arch/arm/repack.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -24,6 +24,7 @@

#define UNUSED GGML_UNUSED

#if defined(__aarch64__) && defined(__ARM_NEON) && (defined(__ARM_FEATURE_MATMUL_INT8) || defined(__ARM_FEATURE_DOTPROD))
static inline void decode_q4_Kx8_scales_mins(const uint8_t * scales_in,
int16x8_t * out_mins,
int8_t * out_scales) {
Expand All @@ -46,6 +47,7 @@ static inline void decode_q4_Kx8_scales_mins(const uint8_t * scales_in,
scales_u32[1] = (sm[2] & kmask2) | (((sm[0] >> 6) & kmask3) << 4);
memcpy(out_scales, scales_u32, 8);
}
#endif

void ggml_quantize_mat_q8_0_4x4(const float * GGML_RESTRICT x, void * GGML_RESTRICT vy, int64_t k) {
assert(QK8_0 == 32);
Expand Down
2 changes: 1 addition & 1 deletion scripts/sync-ggml.last
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1 +1 @@
55bc9320a4aae82af18e23eefd5de319a755d7b9
130bc125a88bb57664b88932c48c38a1cb316fac
Loading