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

models : use absolute paths for the converted model (#1356)

talk-llama : move up-to-date demo to top (#1417)

talk-llama : add an up-to-date demo video

examples : Implement JSON output for Token-Level data in main (#1358)

models : Faster download for models on windows using BitTransfer (#1404)

README : Update README in stream to clarify where to compile from (Issue #1400)

binding : Expose the audio_ctx param through the Go binding (#1368)

README : fix typo (#1362)

docker : Add dockerfile for cublas (#1286)

whisper : abort callback improvements (#1345)

cmake : Abort the build if a requested feature could not be configured (#1350)

cmake : Prefer pkg-config while looking for BLAS (#1349)

models : add conversion scripts from HuggingFace models to CoreML (#1304)

whisper : add abort callback (#1335)

examples : move wav_writer from stream.cpp to common.h (#1317)

whisper : add missing speaker turn API function for whisper_state (#1330)

examples: Update the README for Talk - fixing the gpt2 URL (#1334)

extra: Add benchmark script implemented in Python (#1298)

Examples: Add save audio to file option in stream.cpp (#1310)

readme: Fix spelling error (#1290)

examples: Update README.md of main.cpp (#1306)

binding : fix ruby build by adding missing ggml-alloc (#1305)

bench: fix missing include <cstring> (#1303)

whisper : increase tokenizer buffer (close #1259)

talk-llama : update to latest llama.cpp

sync : ggml (const correctness)

metal : restore matrix x vector f16_f32 kerenls for now

metal : add F32 support + update bench output

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

whisper : fix bench regression + fix performance when using CPU BLAS (#1275)

whisper : faster beam_search sampling via reduced KV cache copies (#1243)

java : fixed signing of java artifact using gradle (#1267)

ci : try to fix gradle action (#1265)

gitignore : update

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

ci : upgrade gradle to 2.4.2 (#1263)

sync : ggml (CUDA faster rope)

cmake : noramlize case (#1129)

build : do not use _GNU_SOURCE gratuitously (#1129)

examples : fix build + compile warnings (close #1256)

models : add quantum models to download-ggml-model.sh (#1235)

whisper.android : bump gradle plugin and dependencies + a lint pass (#1255)

sign jar for Maven Central repo

whisper.android : address ARM's big.LITTLE arch by checking cpu info (#1254)

make : fix detection of AVX2 on macOS (#1250)

ggml : posixify pagesize (#1251)

configured publishing.repositories

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

make : improve cpuinfo handling on x86 hosts (#1238)