stream : add beam size parameter(#2836)

Fixes for Windows (#2790)

node : add max_len params in node addon (#2760)

talk-llama : sync llama.cpp

whisper.objc : fix build and CI

talk-llama : sync llama.cpp

server : fix build (#2718)

talk-llama : sync llama.cpp (#2709)

server : generate unique tmp filenames (#2718)

cli : fix segfault on missing argument (#2700)

objc : rename ggml-cpu-aarch64.c to .cpp (#2687)

examples : handle "main.exe" deprecation

cli : add --suppress_nst support (#2664)

cli : add no_speech_thold (#2663)

server : fix help print

server : add no-speech threshold parameter and functionality (#2654)

whisper : rename suppress_non_speech_tokens to suppress_nst (#2653)

server : add option to suppress non-speech tokens (#2649)

whisper : rename binaries + fix install (#2648)

android : try to fix build

files : remove old sources

talk-llama : sync llama.cpp

common : remove old types

stream : improve consistency in README (#2642)

common : add cstdio header

stream : update build instructions

android : fix build and ci (#2624)

ci : disable CUDA and Android builds

ci : disable Obj-C build + fixes

talk-llama : sync llama.cpp

common : fix compile warning

whisper : adapt to new ggml (wip)

talk-llama : sync llama.cpp

sycl: fix example build (#2570)

whisper.swiftui : switch Mac dest to Mac (Designed for iPad) (#2562)

build : fixes

talk-llama : sync llama.cpp

whisper.swiftui : add model download list & bench methods (#2546)

examples : fix ffmpeg v5 build (#2543)

talk-llama : sync llama.cpp

whisper : add dtw preset for large-v3-turbo (#2481)

objc : fix build

whisper : adapt to latest ggml (skip) (#0)

examples : update dr_wav.h to newer version (#2449)

talk-llama : sync llama.cpp

server : ffmpeg overwrite leftover temp file (#2431)

whisper : add large-v3-turbo (#2440)

make : remove "talk" target until updated

talk-llama : sync llama.cpp

examples : adapt to ggml.h changes (ggml/0)