mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-16 13:20:39 -07:00
e766c7cbfb
* feat(windows): add native ROCm support for AMD GPUs Implements native ROCm architecture for Windows. - Adds backend build pipeline for voicebox-server-rocm.exe - Detects AMD GPUs dynamically and routes PyTorch allocations - Adds automatic download and update logic for ROCm dependencies - Refactors UI in GpuPage.tsx and GpuAcceleration.tsx to add AMD flows - Fixes 'Switch to CPU' lock on Windows via Tauri backend_override state - Resolves PyInstaller/rocm_sdk UnboundLocalError silent crashes - Resolves Numba/NumPy 2.x incompatibilities during Qwen3-TTS load - Resolves HF_HUB_OFFLINE Catch-22 for CustomVoice processor caching * fix(rocm): host libs archive under the app release tag, drop offline-load regression Align the ROCm libs download with the CUDA pattern: both the server core and the libs archive are published under the app-version release tag, with the libs content version encoded in the filename only. The previous code fetched libs from a separate rocm7.2-v1 tag, which disagreed with the download test. Also revert the unrelated Qwen CustomVoice changes that wrapped model loading in force_offline_if_cached (not imported — a NameError on load for every platform) and re-added a Base-model cache gate. The inference-path offline guard was deliberately removed previously. * feat(rocm): gate download on AMD detection and persist the backend variant The ROCm download section now only shows when the backend reports an AMD GPU on Windows (new supports_rocm health field, backed by the memoized is_amd_gpu_windows detection that was previously unused), or when ROCm is already downloaded/active. Make the backend override honor a pinned variant: set_backend_override persists the choice to disk so it survives an app restart, start_server reads it back, and a cuda/rocm pin now actually selects that variant instead of always preferring ROCm. A stale pin to a deleted backend self-heals to the default order rather than forcing CPU. Add the web no-op stub for the new method. * chore(rocm): drop incomplete vitest harness for the unused GpuAcceleration component GpuAcceleration.tsx is not routed anywhere (GpuPage is the live settings view), and the added vitest setup referenced testing-library/vitest deps that were not in the lockfile, breaking the web typecheck. Remove the dead component's test and its scaffolding to keep this PR scoped to the ROCm feature. * ci(rocm): add ROCm release-artifact pipeline Mirror the CUDA packaging path for ROCm so the runtime download has artifacts to fetch. scripts/package_rocm.py splits the PyInstaller --rocm onedir into voicebox-server-rocm.tar.gz (core) + rocm-libs-rocm7.2-v1.tar.gz (AMD runtime: HIP DLLs, rocBLAS Tensile data, MIOpen kernel DBs) + rocm-libs.json, matching the names services/rocm.py expects, both under the app-version release tag. The new build-rocm-windows job in release.yml builds on windows-latest/cp312 and lets build_binary.py --rocm pull the official AMD Radeon wheels. The file classifier can't be validated against a real AMD build on CI, so it has unit coverage (test_package_rocm.py) against a synthetic onedir layout. The prefixes/dir markers may need a tweak after the first real build on AMD hardware — the packager hard-fails loudly if it classifies zero ROCm files. --------- Co-authored-by: Jamie Pine <[email protected]>
80 lines
2.3 KiB
Python
80 lines
2.3 KiB
Python
"""ROCm backend management endpoints."""
|
|
|
|
import logging
|
|
|
|
from fastapi import APIRouter, HTTPException
|
|
from fastapi.responses import StreamingResponse
|
|
|
|
from ..services.task_queue import create_background_task
|
|
from ..utils.progress import get_progress_manager
|
|
|
|
router = APIRouter()
|
|
|
|
logger = logging.getLogger(__name__)
|
|
|
|
|
|
@router.get("/backend/rocm-status")
|
|
async def get_rocm_status():
|
|
"""Get ROCm backend download/availability status."""
|
|
from ..services import rocm
|
|
|
|
return rocm.get_rocm_status()
|
|
|
|
|
|
@router.post("/backend/download-rocm")
|
|
async def download_rocm_backend():
|
|
"""Download the ROCm backend binary."""
|
|
from ..services import rocm
|
|
|
|
progress_manager = get_progress_manager()
|
|
existing = progress_manager.get_progress(rocm.PROGRESS_KEY)
|
|
if existing and existing.get("status") in {"downloading", "extracting"}:
|
|
raise HTTPException(status_code=409, detail="ROCm backend download already in progress")
|
|
|
|
async def _download():
|
|
try:
|
|
await rocm.download_rocm_binary()
|
|
except Exception as e:
|
|
logger.error("ROCm download failed: %s", e)
|
|
|
|
create_background_task(_download())
|
|
return {"message": "ROCm backend download started", "progress_key": rocm.PROGRESS_KEY}
|
|
|
|
|
|
@router.delete("/backend/rocm")
|
|
async def delete_rocm_backend():
|
|
"""Delete the downloaded ROCm backend binary."""
|
|
from ..services import rocm
|
|
|
|
if rocm.is_rocm_active():
|
|
raise HTTPException(
|
|
status_code=409,
|
|
detail="Cannot delete ROCm backend while it is active. Switch to CPU first.",
|
|
)
|
|
|
|
deleted = await rocm.delete_rocm_binary()
|
|
if not deleted:
|
|
raise HTTPException(status_code=404, detail="No ROCm backend found to delete")
|
|
|
|
return {"message": "ROCm backend deleted"}
|
|
|
|
|
|
@router.get("/backend/rocm-progress")
|
|
async def get_rocm_download_progress():
|
|
"""Get ROCm backend download progress via Server-Sent Events."""
|
|
progress_manager = get_progress_manager()
|
|
|
|
async def event_generator():
|
|
async for event in progress_manager.subscribe("rocm-backend"):
|
|
yield event
|
|
|
|
return StreamingResponse(
|
|
event_generator(),
|
|
media_type="text/event-stream",
|
|
headers={
|
|
"Cache-Control": "no-cache",
|
|
"Connection": "keep-alive",
|
|
"X-Accel-Buffering": "no",
|
|
},
|
|
)
|