remove CMAKE_WINDOWS_EXPORT_ALL_SYMBOLS (llama/10797)

Vulkan: Use improved q4_k and q5_k dequant code in dequant shaders (llama/10798)

Vulkan: Add VK_EXT_subgroup_size_control support to ensure full subgroups for coopmats (llama/10721)

ggml: load all backends from a user-provided search path (llama/10699)

vulkan: request round-to-even for fp16 in im2col/rope_head (llama/10767)

vulkan: dynamic subgroup size for the remaining k quants (llama/10745)

CUDA: rename macros to avoid conflicts with WinAPI (llama/10736)

vulkan: disable spirv-opt for coopmat shaders (llama/10763)

ggml : remove return from ggml_gallocr_allocate_node (ggml/1048)

ggml : add check for grad_accs (ggml/1046)

common : remove old types

CUDA: fix shared memory access condition for mmv (llama/10740)

vulkan: fix compile warnings (llama/10731)

Vulkan: fix NaN in tanh.comp with AMD proprietary driver on Windows (llama/10723)

vulkan: compile a test shader in cmake to check for coopmat2 support (llama/10713)

ggml : disable iq4_nl interleave size 8 (llama/10709)

ggml : refactor online repacking (llama/10446)

Vulkan: VK_KHR_cooperative_matrix support to speed up prompt processing (llama/10597)

metal : Extend how Llama.cpp locates metal resources (llama/10676)

vulkan: Add VK_NV_cooperative_matrix2 support for mul_mat and flash attention (llama/10206)

ruby : Add no_speech_thold (#2641)

stream : improve consistency in README (#2642)

whisper : support no_speech_thold (#2625)

whisper : add single-timestamp logic (#2629)

readme : fix typo (#2637)

cmake : fix "amd64" processor string (#2638)

vulkan : fix soft_max.comp division by zero (#2633)

common : add cstdio header

stream : update build instructions

android : fix build and ci (#2624)

models : fix typo in download-ggml-model.sh (#2623)

ruby : Sync whisper.cpp and model download feature (#2617)

scripts : update to new build system

devops : add cmake

devops : update make commands

ggml : remove old files (skip) (#0)

ggml : sync remnants (skip) (#0)

scripts : remove amx from sync

ci : disable freeBSD builds [no ci]

readme : update build instructions

ci : disable CUDA and Android builds

ci : disable Obj-C build + fixes

make : shim cmake

talk-llama : sync llama.cpp

sync : ggml

ggml : add predefined list of CPU backend variants to build (llama/10626)

ggml-cpu : fix HWCAP2_I8MM value (llama/10646)

vulkan: Implement "fast divide" (mul+shift) for unary ops like copy (llama/10642)

SYCL : Move to compile time oneMKL interface backend selection for NVIDIA backend (llama/10584)

Avoid using __fp16 on ARM with old nvcc (llama/10616)