ggml : add ALiBi support for ggml_soft_max_ext (llama/5488)

ggml-alloc : allocate all leafs as if they were inputs (ggml/731)

ggml-alloc : v3 (ggml/727)

ggml alloc: Fix for null dereference on alloc failure (llama/5200)

ggml : add Vulkan backend (llama/2059)

ggml-alloc : add 10% margin to the buffer sizes (llama/5149)

llama : pre-allocate input tensors in a separate buffer (llama/5100)

llama : ggml-backend integration (llama/4766)

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

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

sync : ggml (ggml-alloc + linker + gguf fixes) (#1501)

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

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

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