Commit Graph
6 Commits
Author SHA1 Message Date
73170d0e92 feat(health): warn when GPU arch isn't supported by PyTorch build
Applies the compatibility-checker portion of #367. Adds a
check_cuda_compatibility() helper that compares the current device's
compute capability against torch.cuda._get_arch_list() and returns a
human-readable warning if the PyTorch build doesn't support it.

Wired into three places:
  • HealthResponse gains a gpu_compatibility_warning field so clients
    can surface the issue in the UI
  • Startup logs the warning as WARN level
  • _get_gpu_status() appends "[UNSUPPORTED - see logs]" to the GPU
    label shown in settings

Skipped #367's other half — the switch from stable to nightly cu128
wheels across release.yml, build_binary.py, and justfile. That's
redundant with #401's TORCH_CUDA_ARCH_LIST=...12.0+PTX approach and
would introduce non-deterministic builds from shifting nightly
releases.

Co-Authored-By: nyzxor <[email protected]>
Co-Authored-By: Claude Opus 4.6 (1M context) <[email protected]>
2026-04-16 02:11:23 -07:00
James Pine 707046237c fix: complete Intel XPU support — device-aware seeding, GPU status reporting, and setup detection
Address CodeRabbit review feedback and user-reported GPU acceleration failure:

- Use shared manual_seed() in chatterbox, chatterbox_turbo, and luxtts
  backends so XPU (and future accelerators) get proper device seeding
- Add XPU branch to _get_gpu_status() so startup log reports Intel Arc
  GPUs instead of 'None (CPU only)'
- Add XPU VRAM reporting and correct backend_variant fallback in the
  /health endpoint
- Switch justfile GPU detection from Get-WmiObject to Get-CimInstance,
  simplify the Arc regex to match 'Arc' (not 'Intel.*Arc'), log
  detected GPUs, and print manual install instructions on miss

Resolves the root cause where IPEX was silently not installed due to
WMI detection failure, causing CPU-only fallback on Intel Arc systems.
2026-03-18 17:01:12 -07:00
James Pine 1526f2de26 about page + generation folder open and display 2026-03-16 10:14:47 -07:00
James Pine 4a8a9eac14 fix: docker frontend + docs cleanup 2026-03-16 05:28:05 -07:00
James Pine b3012ed10c move CRUD and service modules into services/, platform_detect into utils/
Move 9 business-logic modules from the backend root into services/:
channels, effects, history, profiles, stories, versions, export_import,
transcribe, tts. Move platform_detect.py into utils/.

Backend root now contains only infrastructure (app, main, config, server,
models, build_binary) and docs. All 94 routes verified.
2026-03-16 02:15:20 -07:00
James Pine 88536d27f7 extract routes from main.py into domain routers (Phase 4)
Split the 2,578-line main.py (90 routes) into 12 domain-specific router
modules under routes/. main.py is now a 45-line entry point.

New structure:
- app.py: FastAPI instance, CORS, startup/shutdown, safe_content_disposition
- routes/: health, profiles, channels, generations, history, transcription,
  stories, effects, audio, models, tasks, cuda
- services/cuda.py: moved from cuda_download.py

Also includes Phase 5 database/ package (from parallel agent):
- database/__init__.py re-exports all symbols for backward compat
- database/models.py, session.py, migrations.py, seed.py

All 90 routes verified registered and app imports cleanly.
2026-03-16 02:03:15 -07:00