Merge branch 'upstream' into concedo_experimental

# Conflicts:
#	.github/workflows/build-android.yml
#	.github/workflows/build-apple.yml
#	.github/workflows/build-cpu.yml
#	.github/workflows/build-cuda-ubuntu.yml
#	.github/workflows/build-cuda-windows.yml
#	.github/workflows/build-msys.yml
#	.github/workflows/build-opencl.yml
#	.github/workflows/build-openvino.yml
#	.github/workflows/build-riscv.yml
#	.github/workflows/build-sanitize.yml
#	.github/workflows/build-sycl.yml
#	.github/workflows/build-vulkan.yml
#	.github/workflows/build-wasm.yml
#	.github/workflows/build-webgpu.yml
#	.github/workflows/copilot-setup-steps.yml
#	.github/workflows/hip-quality-check.yml
#	.github/workflows/release.yml
#	.github/workflows/server.yml
#	CODEOWNERS
#	build-xcframework.sh
#	docs/android.md
#	docs/backend/SYCL.md
#	docs/build.md
#	ggml/CMakeLists.txt
#	ggml/src/ggml-cpu/CMakeLists.txt
#	ggml/src/ggml-cpu/kleidiai/kleidiai.cpp
#	ggml/src/ggml-hexagon/ggml-hexagon.cpp
#	ggml/src/ggml-hexagon/htp-opnode.h
#	ggml/src/ggml-hexagon/htp/cpy-ops.c
#	ggml/src/ggml-hexagon/htp/gated-delta-net-ops.c
#	ggml/src/ggml-hexagon/htp/get-rows-ops.c
#	ggml/src/ggml-hexagon/htp/htp-ctx.h
#	ggml/src/ggml-hexagon/htp/htp-ops.h
#	ggml/src/ggml-hexagon/htp/main.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.c
#	ggml/src/ggml-hexagon/htp/matmul-ops.h
#	ggml/src/ggml-hexagon/htp/set-rows-ops.c
#	ggml/src/ggml-metal/CMakeLists.txt
#	ggml/src/ggml-opencl/ggml-opencl.cpp
#	ggml/src/ggml-opencl/kernels/gemv_noshuffle_q4_k_f32.cl
#	ggml/src/ggml-sycl/ggml-sycl.cpp
#	tests/CMakeLists.txt
#	tests/test-backend-ops.cpp
#	tests/test-llama-archs.cpp
#	tests/test-save-load-state.cpp
#	tools/mtmd/CMakeLists.txt
This commit is contained in:
Concedo
2026-09-02 23:24:09 +08:00
74 changed files with 4125 additions and 611 deletions
+6
View File
@@ -2471,6 +2471,12 @@ extern "C" {
GGML_API enum ggml_prec ggml_flash_attn_ext_get_prec(
const struct ggml_tensor * a);
// Use finite mask entries as a sparse K/V set. Set 0 to disable.
// n_kv_max must bound the number of finite entries in every mask row.
GGML_API void ggml_flash_attn_ext_set_n_kv_max(
struct ggml_tensor * a,
int32_t n_kv_max);
GGML_API void ggml_flash_attn_ext_add_sinks(
struct ggml_tensor * a,
struct ggml_tensor * sinks);