metal : use autoreleasepool to avoid memory leaks (llama/5437)

metal : option to embed MSL source into compiled binary (#1842)

metal : add im2col F32 dst support (llama/5132)

SOTA 3-bit quants (llama/5196)

ggml : add max buffer sizes to opencl and metal backends (llama/5181)

metal : free metal objects (llama/5161)

ci : fix yolo URLs + fix metal capture (ggml/712)

metal : add debug capture backend function (ggml/694)

ggml : add Vulkan backend (llama/2059)

metal : remove unused `n_buffers` and `buffers` (llama/5129)

metal : show compile log messages

metal : disable support for MUL_MAT F32 x F16

ggml : sync ggml-metal.m

metal : create autorelease pool during library build (llama/4970)

metal : log `recommendedMaxWorkingSetSize` on iOS 16+ (llama/4936)

ggml : introduce GGML_CALL function annotation (llama/4850)

metal : correctly set SIMD support flags on iOS (llama/4923)

metal : remove old API (llama/4919)

metal : disable log for loaded kernels (llama/4794)

metal : refactor kernel loading code (llama/4794)

llama : ggml-backend integration (llama/4766)

ggml : SOTA 2-bit quants (add IQ2_XS) (llama/4856)

metal : put encoder debug group behind a define (llama/4873)

metal : fix deprecation warning (ggml/690)

metal : wrap each operation in debug group (ggml/690)

SOTA 2-bit quants (llama/4773)

metal : switch back to default.metallib (ggml/681)

ggml : add error handling to graph_compute (#1714)

metal : add kernel_get_rows_i32

metal : optimize ggml_mul_mat_id (faster Mixtral PP) (llama/4725)

metal : enable shader debugging (cmake option) (llama/4705)

sync : ggml (ggml_scale, ggml_row_size, etc.) (#1677)

sync : ggml (Metal fixes, new ops, tests) (#1633)

metal : fix `ggml_metal_log` vargs (#1606)

metal : fix soft_max kernel src1 argument (#1602)

sync : ggml (new ops, new backend, etc) (#1602)

metal : add backend function to check device family support (#1547)

metal : fix build (#1544)

whisper : make large version explicit + fix data size units (#1493)

ggml : fix some compile warnings

whisper : add full CUDA and Metal offloading (#1472)

metal : fix asserts for setThreadgroupMemoryLength (close #1435)

sync : ggml (backend v2, k-quants, CUDA opts, Metal opts, etc.) (#1422)

metal : restore matrix x vector f16_f32 kerenls for now

metal : add F32 support + update bench output

whisper : Metal and ggml-alloc support (#1270)

sync : ggml (HBM + Metal + style) (#1264)

ggml : posixify pagesize (#1251)

ggml : sync latest llama.cpp (view_src + alloc improvements) (#1247)

ggml : sync (ggml-alloc, GPU, eps, etc.) (#1220)