files : rename ./extra to ./scripts

whisper : fix DTW memory access (#2012)

common : fix file-handle leak in read_wav() (#2026)

main : set stdin to binary mode on Windows (#2025)

cmake : support for CPU BLAS build via Intel MKL (#2024)

main : allow a response-file as the sole parameter (#2019)

whisper : suppress tokens with a regex (#1997)

cmake : create solution folders (#2004)

sync : ggml

extra : sync grammar-parser

talk-llama : sync llama.cpp

sync : ggml

sync : llama.cpp (skip)

Fixed minor bug when enabling FP16 for non intel targets (llama/6464)

ggml : mul_mat_id use the same tensor for all the experts (llama/6387)

Disable iqx on windows as WA (llama/6435)

Vulkan k-quant mmq and ggml-backend offload functionality (llama/6155)

fix set main gpu crash (llama/6339)

ggml : fix bounds checking of zero size views (llama/6347)

backend : fix typo in scheduler documentation (ggml/781)

extra : sync ggml-cuda folder

ggml: bypass code incompatible with CUDA < 11.1 (#2020)

ci : add building in MSYS2 environments (Windows) (#1994)

build : use pkg-config for OpenBLAS (#1778)

main : add command-style grammar (#1998)

make : add grammar parser to common objects

sync : ggml (#2001)

whisper : improve handling of prompts (#1981)

whisper : improve support for distil-large-v3 (#1982)

ruby : fix build (#1980)

docker : libcuda.so.1 in PATH (#1966)

readme : add Fedora dependencies (#1970)

whisper : token-level timestamps with DTW (#1485)

examples : rename --audio-context to --audio-ctx per help text (#1953)

whisper : set outputs from conv graph (#1959)

alloc : fix allocation data of pre-allocated leafs

cmake : copy ggml-common.h to bin

gitignore : .vimspector.json

talk-llama : sync llama.cpp

sync : ggml

update examples and tests

ggml : add ggml-common.h

ggml : designate enum vals for integer types (llama/6050)

metal : build metallib + fix embed path (llama/6015)

llama : add pipeline parallelism support (llama/6017)

Update get version (llama/6025)

ggml : reuse quantum structs across backends (llama/5943)

ggml : fix UB in IQ2_S and IQ3_S (llama/6012)

sycl : update IQ1_S kernels (WIP - not working!) (llama/5995)

1.5 bit: we can do even better (llama/5999)