1.5 bit quantization (llama/5453)

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

ggml : add numa options (llama/5377)

ggml : add mmla kernels for quantized GEMM (llama/4966)

ggml-alloc : v3 (ggml/727)

llava : add MobileVLM support (llama/5132)

kompute : llama-bench support and ggml_cpu_has_kompute() (llama/5226)

ggml : add abort_callback for cpu backend (ggml/725)

SOTA 3-bit quants (llama/5196)

ggml : add Vulkan backend (llama/2059)

ggml : add unified SYCL backend for Intel GPUs (llama/2690)

minor : clean-up some warnings and style (llama/5094)

llava : MobileVLM support (llama/4954)

ggml : add IQ2 to test-backend-ops + refactoring (llama/4990)

imatrix : offload to GPU support (llama/4957)

ggml : introduce GGML_CALL function annotation (llama/4850)

2-bit quantizations (llama/4897)

llama : ggml-backend integration (llama/4766)

Importance Matrix calculation (llama/4861)

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

ggml : remove ggml_cpy_inplace and ggml_cont_inplace (ggml/693)

ggml : change GGML_MAX_NAME at compile time (ggml/682)

SOTA 2-bit quants (llama/4773)

ggml : add ggml_cpu_has_avx_vnni() (llama/4589)

sync : ggml (VMM, sync-ggml-am, dotprod ARM fixes, CUDA fixes) (#1691)

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

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

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

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

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

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

sync : ggml (const correctness)

metal : add F32 support + update bench output

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

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

ggml : detect SSSE3 (#1211)

ggml : sync latest repo (mostly refactoring changes)

ggml : sync latest ggml lib

ggml : sync latest ggml repo

ggml : sync latest ggml

ggml : sync ggml (clBLAST + tensor names)

whisper : add integer quantization support (#540)

ggml : sync with ggml repo (warning fixes + asserts)

ggml : sync latest ggml + llama.cpp updates (quantization)

ggml : sync latest ggml

ggml : sync latest changes from ggml and llama.cpp

ggml : backport llama.cpp updates (close #709)

talk-llama : add new example + sync ggml from llama.cpp (#664)

whisper : reduce memory usage during inference (#431)

ggml : add SSE3 and fp16 conversion lookup table (#368)