talk-llama : sync llama.cpp

talk-llama : stream response (#1121)

talk-llama : sync llama.cpp

talk-llama : sync llama.cpp

sync : llama.cpp

talk-llama : optional wake-up command and audio confirmation (#1765)

talk-llama : sync llama.cpp

talk-llama : llama.cpp

talk-llama : sync llama.cpp

talk-llama : add optional CLI arg to set the bot name (#1764)

talk-llama : sync llama.cpp

talk-llama : sync llama.cpp

talk-llama : add optional Piper TTS support (#1749)

talk-llama : sync latest llama.cpp

ci : build with CLBlast + ggml-opencl use GGML_API (#1576)

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

examples : Revert CMakeLists.txt for talk-llama (#1669)

cmake : target windows 8 or above for prefetchVirtualMemory in llama-talk (#1617)

talk-llama : improve quote and backtick handling (#1364)

talk-llama : enable GPU by default

talk-llama : add n_gpu_layers parameter (#1475)

talk-llama : add language auto detect (#1467)

cmake : fix talk-llama build

talk-llama : fix n_gpu_layers usage again (#1442)

examples : fix n_gpu_layers usage in talk-llama (#1441)

whisper : add context param to disable gpu (#1293)

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

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

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

talk-llama : update to latest llama.cpp

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

build : do not use _GNU_SOURCE gratuitously (#1129)

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

talk-llama : fix new rope interface

Revert "ggml : do not use _GNU_SOURCE gratuitously (#1027)"

talk-llama : fix build on macOS (#1062)

ggml : do not use _GNU_SOURCE gratuitously (#1027)

talk-llama : fix build after ggml sync (#1049)

`speak` scripts for Windows

examples : update elevenlabs scripts to use official python API (#837)

talk-llama : sync latest llama.cpp (close #922, close #954)

talk-llama : fix build + sync latest llama.cpp

talk-llama : only copy used KV cache in get / set state (#890)

talk-llama : fix session prompt load (#854)

talk-llama : add --session support (#845)

whisper : add integer quantization support (#540)

whisper : add GPU support via cuBLAS (#834)

talk, talk-llama : add basic example script for eleven-labs tts (#728)

talk-llama : correct default speak.sh path (#720)

talk-llama : increase context to 2048