aboutsummaryrefslogtreecommitdiff
path: root/app/backends
AgeCommit message (Collapse)Author
2026-09-02fix: warn before using a likely too-big chunk size for sglang-omni modelshistoria
2026-09-02feat: reserve 20% vram when running higgs with sglang-omnihistoria
2026-09-02feat: sglang-omni model picker on manual server launchhistoria
2026-09-02fix: ZONOS2 only generating 1024 tokens maxhistoria
2026-09-02feat: auto-update via settingshistoria
2026-09-02feat: sglang backend supporthistoria
2026-09-01slop refactor/deduphistoria
2026-09-01fix: spec santizer for glm, outetts, miotts, minimax.historia
2026-09-01fix: hide speech-to-speech only models from config wizardhistoria
2026-08-30fix: non-clone models correctly supported in tui, restart server when neededhistoria
2026-08-29fix: crash on bad model_specs from audio.cpp, sanitizedhistoria
2026-08-28feat(audio.cpp): if github binary download fails, automatically start ↵historia
building from source
2026-08-28feat: offer to download prebuilt mac/win binaries, new macos build fallback ↵historia
if xcode is not installed
2026-08-28feat: cli auto-starts and stops locally-managed servers if no --api-url is ↵historia
passed
2026-08-28feat: run auto-build audio.cpp scripts for macos and windowshistoria
2026-08-28refactor: overhaul config.py, remove cli default optionshistoria
2026-08-28fix: remove backtrace from console output when using incorrect/incomplete ↵historia
cli flags
2026-08-28feat: .wav hints for all voice directory pickers in tuihistoria
2026-08-28fix: system python used instead of venv python, breaking whisper transcriptionhistoria
2026-08-28remove: unnecessary flash on succesful buildhistoria
2026-08-28feat: unified logging with logging_kit.pyhistoria
2026-08-28feat: cuda arch detection for shorter builds, build failure detectionhistoria
2026-08-28feat: qwen-tts backend widgets updated to same style as audio.cpphistoria
2026-08-28fix: silently failing whisper transcriptionhistoria
2026-08-27remove: unnecessary tui texthistoria
2026-08-27feat: help menu in tuihistoria
2026-08-27feat: automatic updates added to configure backend menuhistoria
2026-08-27feat: separate venvs for qwen-tts and faster, manage (un)installshistoria
2026-08-26feat: manage qwen-tts model installs manually, delete model(s) when uninstalledhistoria
2026-08-26feat: design model support for qwen-tts backend. remove unnecessary port ↵historia
split for qwen models
2026-08-26fix: settings menu only prompts to save after changehistoria
2026-08-26feat: language and option fields in tui, context-sensitive voice labelhistoria
2026-08-26feat: in-place toggle field, updated transcription tui to use new fieldhistoria
2026-08-26fix: default directory when choosing voices in tuihistoria
2026-08-26feat: combined install/configure tui screens into one menu, removed ↵historia
extraneous wizard screens
2026-08-26refactor: put shared ui screen code into ui.viewkithistoria
2026-08-26refactor: audiocpp.py setup flowhistoria
2026-08-26refactor: split tts.py into per-backend packageshistoria
2026-08-26fix: broken venv importshistoria
2026-08-26refactor(audiocpp): pin checkout to app/audio.cpp, report install resultshistoria
2026-08-26fix: harden server start/stop guardshistoria
2026-08-25feat: stop server and exit after generatinghistoria
2026-08-25fix: tui errors wait for getch()historia
2026-08-25feat: no console drop when uninstalling backendshistoria
2026-08-25fix: build audio.cpp with --deployment-buildhistoria
2026-08-25feat: better tui menu option gating for models that support custom voices ↵historia
(qwen) and models that do not support instructions
2026-08-25fix: detect if all audio.cpp models already downloadedhistoria
2026-08-25feat: automatically name audio.cpp model ids with long namehistoria
2026-08-25feat(tui): simultaneous build and model downloadhistoria
2026-08-25fix: automatic patch for top-k.cu to file ggml build errorhistoria
generated by cgit v1.2.3 (git 2.25.1) at 2026-10-24 13:11:12 +0000