aboutsummaryrefslogtreecommitdiff
path: root/app/backends
AgeCommit message (Collapse)Author
4 daysfix: sglomni retry contract, booting detection, CLI keys, companion refresh, ↵HEADmainhistoria
ffmpeg dep
4 daysrefactor: share the HF cache helpers between qwen and sglomnihistoria
5 daysfeat: pip install checks for bad crc errors and purges cache automaticallyhistoria
5 daysfix: increase gpu memory for MOSS with gplang-omni to .87historia
5 daysfeat: gplang-omni reserves 70% of gpu 0 memory, preventing oom errors on ↵historia
consumer cards
5 daysfix: warn before using a likely too-big chunk size for sglang-omni modelshistoria
5 daysfeat: reserve 20% vram when running higgs with sglang-omnihistoria
5 daysfeat: sglang-omni model picker on manual server launchhistoria
5 daysfix: ZONOS2 only generating 1024 tokens maxhistoria
6 daysfeat: auto-update via settingshistoria
6 daysfeat: sglang backend supporthistoria
7 daysslop refactor/deduphistoria
7 daysfix: spec santizer for glm, outetts, miotts, minimax.historia
7 daysfix: hide speech-to-speech only models from config wizardhistoria
8 daysfix: non-clone models correctly supported in tui, restart server when neededhistoria
10 daysfix: crash on bad model_specs from audio.cpp, sanitizedhistoria
10 daysfeat(audio.cpp): if github binary download fails, automatically start ↵historia
building from source
10 daysfeat: offer to download prebuilt mac/win binaries, new macos build fallback ↵historia
if xcode is not installed
11 daysfeat: cli auto-starts and stops locally-managed servers if no --api-url is ↵historia
passed
11 daysfeat: run auto-build audio.cpp scripts for macos and windowshistoria
11 daysrefactor: overhaul config.py, remove cli default optionshistoria
11 daysfix: remove backtrace from console output when using incorrect/incomplete ↵historia
cli flags
11 daysfeat: .wav hints for all voice directory pickers in tuihistoria
11 daysfix: system python used instead of venv python, breaking whisper transcriptionhistoria
11 daysremove: unnecessary flash on succesful buildhistoria
11 daysfeat: unified logging with logging_kit.pyhistoria
11 daysfeat: cuda arch detection for shorter builds, build failure detectionhistoria
11 daysfeat: qwen-tts backend widgets updated to same style as audio.cpphistoria
11 daysfix: silently failing whisper transcriptionhistoria
11 daysremove: unnecessary tui texthistoria
12 daysfeat: help menu in tuihistoria
12 daysfeat: automatic updates added to configure backend menuhistoria
12 daysfeat: separate venvs for qwen-tts and faster, manage (un)installshistoria
12 daysfeat: manage qwen-tts model installs manually, delete model(s) when uninstalledhistoria
12 daysfeat: design model support for qwen-tts backend. remove unnecessary port ↵historia
split for qwen models
12 daysfix: settings menu only prompts to save after changehistoria
12 daysfeat: language and option fields in tui, context-sensitive voice labelhistoria
12 daysfeat: in-place toggle field, updated transcription tui to use new fieldhistoria
12 daysfix: default directory when choosing voices in tuihistoria
13 daysfeat: combined install/configure tui screens into one menu, removed ↵historia
extraneous wizard screens
13 daysrefactor: put shared ui screen code into ui.viewkithistoria
13 daysrefactor: audiocpp.py setup flowhistoria
13 daysrefactor: split tts.py into per-backend packageshistoria
13 daysfix: broken venv importshistoria
13 daysrefactor(audiocpp): pin checkout to app/audio.cpp, report install resultshistoria
13 daysfix: harden server start/stop guardshistoria
13 daysfeat: stop server and exit after generatinghistoria
13 daysfix: tui errors wait for getch()historia
14 daysfeat: no console drop when uninstalling backendshistoria
14 daysfix: build audio.cpp with --deployment-buildhistoria
generated by cgit v1.2.3 (git 2.25.1) at 2026-09-08 10:12:59 +0000