mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-16 13:20:39 -07:00
* 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]>
This commit is contained in:
Juan C Muñoz P
co-authored by
Jamie Pine
Jamie Pine
parent
c2282b256a
commit
e766c7cbfb
@@ -340,3 +340,64 @@ jobs:
|
||||
name: voicebox-server-cuda-windows
|
||||
path: backend/dist/voicebox-server-cuda/
|
||||
retention-days: 7
|
||||
|
||||
build-rocm-windows:
|
||||
runs-on: windows-latest
|
||||
permissions:
|
||||
contents: write
|
||||
|
||||
steps:
|
||||
- uses: actions/checkout@v4
|
||||
|
||||
- name: Setup Python
|
||||
uses: actions/setup-python@v5
|
||||
with:
|
||||
# ROCm wheels are cp312-cp312-specific — build_binary.py --rocm enforces this.
|
||||
python-version: "3.12"
|
||||
cache: "pip"
|
||||
|
||||
- name: Install Python dependencies
|
||||
run: |
|
||||
python -m pip install --upgrade pip
|
||||
pip install pyinstaller
|
||||
pip install -r backend/requirements.txt
|
||||
pip install --no-deps chatterbox-tts
|
||||
pip install --no-deps hume-tada
|
||||
|
||||
- name: Build ROCm server binary (onedir)
|
||||
shell: bash
|
||||
working-directory: backend
|
||||
# build_binary.py --rocm pulls the official AMD Radeon torch + rocm_sdk
|
||||
# wheels (rocm-rel-7.2.1) itself when ROCm torch is not already present,
|
||||
# then restores the dev torch afterwards.
|
||||
run: python build_binary.py --rocm
|
||||
|
||||
- name: Package into server core + ROCm libs archives
|
||||
shell: bash
|
||||
run: |
|
||||
python scripts/package_rocm.py \
|
||||
backend/dist/voicebox-server-rocm/ \
|
||||
--output release-assets/ \
|
||||
--rocm-libs-version rocm7.2-v1 \
|
||||
--torch-compat ">=2.9.0,<2.10.0"
|
||||
|
||||
- name: Upload archives to GitHub Release
|
||||
if: startsWith(github.ref, 'refs/tags/')
|
||||
uses: softprops/action-gh-release@v2
|
||||
with:
|
||||
files: |
|
||||
release-assets/voicebox-server-rocm.tar.gz
|
||||
release-assets/voicebox-server-rocm.tar.gz.sha256
|
||||
release-assets/rocm-libs-rocm7.2-v1.tar.gz
|
||||
release-assets/rocm-libs-rocm7.2-v1.tar.gz.sha256
|
||||
release-assets/rocm-libs.json
|
||||
draft: true
|
||||
env:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
|
||||
- name: Upload onedir as workflow artifact
|
||||
uses: actions/upload-artifact@v4
|
||||
with:
|
||||
name: voicebox-server-rocm-windows
|
||||
path: backend/dist/voicebox-server-rocm/
|
||||
retention-days: 7
|
||||
|
||||
BIN
Binary file not shown.
@@ -5,7 +5,7 @@ import { Button } from '@/components/ui/button';
|
||||
import { Card, CardContent, CardHeader, CardTitle } from '@/components/ui/card';
|
||||
import { Progress } from '@/components/ui/progress';
|
||||
import { apiClient } from '@/lib/api/client';
|
||||
import type { CudaDownloadProgress } from '@/lib/api/types';
|
||||
import type { CudaDownloadProgress, RocmDownloadProgress } from '@/lib/api/types';
|
||||
import { useServerHealth } from '@/lib/hooks/useServer';
|
||||
import { usePlatform } from '@/platform/PlatformContext';
|
||||
import { useServerStore } from '@/stores/serverStore';
|
||||
@@ -21,6 +21,9 @@ export function GpuAcceleration() {
|
||||
const [restartPhase, setRestartPhase] = useState<RestartPhase>('idle');
|
||||
const [error, setError] = useState<string | null>(null);
|
||||
const [downloadProgress, setDownloadProgress] = useState<CudaDownloadProgress | null>(null);
|
||||
const [rocmDownloadProgress, setRocmDownloadProgress] = useState<RocmDownloadProgress | null>(
|
||||
null,
|
||||
);
|
||||
const healthPollRef = useRef<ReturnType<typeof setInterval> | null>(null);
|
||||
|
||||
// Query CUDA backend status
|
||||
@@ -36,10 +39,26 @@ export function GpuAcceleration() {
|
||||
enabled: !!health, // Only fetch when backend is reachable
|
||||
});
|
||||
|
||||
// Query ROCm backend status
|
||||
const {
|
||||
data: rocmStatus,
|
||||
isLoading: _rocmStatusLoading,
|
||||
refetch: refetchRocmStatus,
|
||||
} = useQuery({
|
||||
queryKey: ['rocm-status', serverUrl],
|
||||
queryFn: () => apiClient.getRocmStatus(),
|
||||
refetchInterval: (query) => (query.state.status === 'pending' ? false : 10000),
|
||||
retry: 1,
|
||||
enabled: !!health, // Only fetch when backend is reachable
|
||||
});
|
||||
|
||||
// Derived state
|
||||
const isCurrentlyCuda = health?.backend_variant === 'cuda';
|
||||
const isCurrentlyRocm = health?.backend_variant === 'rocm';
|
||||
const cudaAvailable = cudaStatus?.available ?? false;
|
||||
const cudaDownloading = cudaStatus?.downloading ?? false;
|
||||
const rocmAvailable = rocmStatus?.available ?? false;
|
||||
const rocmDownloading = rocmStatus?.downloading ?? false;
|
||||
|
||||
// Clean up health poll on unmount
|
||||
useEffect(() => {
|
||||
@@ -51,7 +70,7 @@ export function GpuAcceleration() {
|
||||
};
|
||||
}, []);
|
||||
|
||||
// SSE progress tracking during download
|
||||
// SSE progress tracking during CUDA download
|
||||
useEffect(() => {
|
||||
if (!cudaDownloading || !serverUrl) {
|
||||
return;
|
||||
@@ -88,6 +107,43 @@ export function GpuAcceleration() {
|
||||
};
|
||||
}, [cudaDownloading, serverUrl, refetchCudaStatus]);
|
||||
|
||||
// SSE progress tracking during ROCm download
|
||||
useEffect(() => {
|
||||
if (!rocmDownloading || !serverUrl) {
|
||||
return;
|
||||
}
|
||||
|
||||
const eventSource = new EventSource(`${serverUrl}/backend/rocm-progress`);
|
||||
|
||||
eventSource.onmessage = (event) => {
|
||||
try {
|
||||
const data = JSON.parse(event.data) as RocmDownloadProgress;
|
||||
setRocmDownloadProgress(data);
|
||||
|
||||
if (data.status === 'complete') {
|
||||
eventSource.close();
|
||||
setRocmDownloadProgress(null);
|
||||
refetchRocmStatus();
|
||||
} else if (data.status === 'error') {
|
||||
eventSource.close();
|
||||
setError(data.error || 'Download failed');
|
||||
setRocmDownloadProgress(null);
|
||||
refetchRocmStatus();
|
||||
}
|
||||
} catch (e) {
|
||||
console.error('Error parsing ROCm progress event:', e);
|
||||
}
|
||||
};
|
||||
|
||||
eventSource.onerror = () => {
|
||||
eventSource.close();
|
||||
};
|
||||
|
||||
return () => {
|
||||
eventSource.close();
|
||||
};
|
||||
}, [rocmDownloading, serverUrl, refetchRocmStatus]);
|
||||
|
||||
// Start aggressive health polling during restart
|
||||
const startHealthPolling = useCallback(() => {
|
||||
if (healthPollRef.current) return;
|
||||
@@ -113,7 +169,7 @@ export function GpuAcceleration() {
|
||||
}, 1000);
|
||||
}, [queryClient]);
|
||||
|
||||
const handleDownload = async () => {
|
||||
const handleDownloadCuda = async () => {
|
||||
setError(null);
|
||||
try {
|
||||
await apiClient.downloadCudaBackend();
|
||||
@@ -128,6 +184,21 @@ export function GpuAcceleration() {
|
||||
}
|
||||
};
|
||||
|
||||
const handleDownloadRocm = async () => {
|
||||
setError(null);
|
||||
try {
|
||||
await apiClient.downloadRocmBackend();
|
||||
refetchRocmStatus();
|
||||
} catch (e: unknown) {
|
||||
const msg = e instanceof Error ? e.message : 'Failed to start download';
|
||||
if (msg.includes('already downloaded')) {
|
||||
refetchRocmStatus();
|
||||
} else {
|
||||
setError(msg);
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
const handleRestart = async () => {
|
||||
setError(null);
|
||||
setRestartPhase('stopping');
|
||||
@@ -154,18 +225,17 @@ export function GpuAcceleration() {
|
||||
}
|
||||
};
|
||||
|
||||
const handleSwitchToCpu = async () => {
|
||||
// To switch to CPU: delete the CUDA binary, then restart.
|
||||
// start_server always prefers CUDA if present, so we must remove it first.
|
||||
const handleSwitchToCpuFromCuda = async () => {
|
||||
setError(null);
|
||||
setRestartPhase('stopping');
|
||||
|
||||
try {
|
||||
await apiClient.deleteCudaBackend();
|
||||
// Tell Rust launcher to skip GPU binary detection on next start.
|
||||
// We cannot delete an active .exe on Windows, so we override instead.
|
||||
await platform.lifecycle.setBackendOverride('cpu');
|
||||
setRestartPhase('waiting');
|
||||
startHealthPolling();
|
||||
await platform.lifecycle.restartServer();
|
||||
// Invoke resolved — server is likely ready
|
||||
if (healthPollRef.current) {
|
||||
clearInterval(healthPollRef.current);
|
||||
healthPollRef.current = null;
|
||||
@@ -184,7 +254,36 @@ export function GpuAcceleration() {
|
||||
}
|
||||
};
|
||||
|
||||
const handleDelete = async () => {
|
||||
const handleSwitchToCpuFromRocm = async () => {
|
||||
setError(null);
|
||||
setRestartPhase('stopping');
|
||||
|
||||
try {
|
||||
// Tell Rust launcher to skip GPU binary detection on next start.
|
||||
// We cannot delete an active .exe on Windows, so we override instead.
|
||||
await platform.lifecycle.setBackendOverride('cpu');
|
||||
setRestartPhase('waiting');
|
||||
startHealthPolling();
|
||||
await platform.lifecycle.restartServer();
|
||||
if (healthPollRef.current) {
|
||||
clearInterval(healthPollRef.current);
|
||||
healthPollRef.current = null;
|
||||
}
|
||||
setRestartPhase('ready');
|
||||
queryClient.invalidateQueries();
|
||||
setTimeout(() => setRestartPhase('idle'), 2000);
|
||||
} catch (e: unknown) {
|
||||
setRestartPhase('idle');
|
||||
if (healthPollRef.current) {
|
||||
clearInterval(healthPollRef.current);
|
||||
healthPollRef.current = null;
|
||||
}
|
||||
setError(e instanceof Error ? e.message : 'Failed to switch to CPU');
|
||||
refetchRocmStatus();
|
||||
}
|
||||
};
|
||||
|
||||
const handleDeleteCuda = async () => {
|
||||
setError(null);
|
||||
try {
|
||||
await apiClient.deleteCudaBackend();
|
||||
@@ -194,6 +293,16 @@ export function GpuAcceleration() {
|
||||
}
|
||||
};
|
||||
|
||||
const handleDeleteRocm = async () => {
|
||||
setError(null);
|
||||
try {
|
||||
await apiClient.deleteRocmBackend();
|
||||
refetchRocmStatus();
|
||||
} catch (e: unknown) {
|
||||
setError(e instanceof Error ? e.message : 'Failed to delete ROCm backend');
|
||||
}
|
||||
};
|
||||
|
||||
const formatBytes = (bytes: number): string => {
|
||||
if (bytes === 0) return '0 B';
|
||||
const k = 1024;
|
||||
@@ -205,7 +314,7 @@ export function GpuAcceleration() {
|
||||
// Don't render until health data is available
|
||||
if (!health) return null;
|
||||
|
||||
// If the system already has native GPU (MPS, etc.), only show info - no CUDA needed
|
||||
// If the system already has native GPU (MPS, ROCm active, etc.), only show info - no download needed
|
||||
const hasNativeGpu =
|
||||
health.gpu_available &&
|
||||
!isCurrentlyCuda &&
|
||||
@@ -241,8 +350,6 @@ export function GpuAcceleration() {
|
||||
)}
|
||||
</div>
|
||||
|
||||
{/* Native GPU detected - no CUDA download needed */}
|
||||
|
||||
{/* Currently running CUDA - show switch back to CPU */}
|
||||
{isCurrentlyCuda && platform.metadata.isTauri && (
|
||||
<>
|
||||
@@ -261,7 +368,12 @@ export function GpuAcceleration() {
|
||||
Running with CUDA GPU acceleration. Switch back to CPU if needed (you can
|
||||
re-download later).
|
||||
</p>
|
||||
<Button onClick={handleSwitchToCpu} variant="outline" className="w-full" size="sm">
|
||||
<Button
|
||||
onClick={handleSwitchToCpuFromCuda}
|
||||
variant="outline"
|
||||
className="w-full"
|
||||
size="sm"
|
||||
>
|
||||
<RotateCw className="h-4 w-4 mr-2" />
|
||||
Switch to CPU Backend
|
||||
</Button>
|
||||
@@ -276,39 +388,207 @@ export function GpuAcceleration() {
|
||||
</>
|
||||
)}
|
||||
|
||||
{/* CUDA download/manage section - show when no native GPU and not currently running CUDA */}
|
||||
{!hasNativeGpu && !isCurrentlyCuda && (
|
||||
{/* Currently running ROCm - show switch back to CPU */}
|
||||
{isCurrentlyRocm && platform.metadata.isTauri && (
|
||||
<>
|
||||
{/* Download progress (manual download or auto-update) */}
|
||||
{cudaDownloading && downloadProgress && (
|
||||
<div className="space-y-2">
|
||||
<div className="flex items-center justify-between text-sm">
|
||||
<div className="flex items-center gap-2">
|
||||
<Loader2 className="h-4 w-4 animate-spin" />
|
||||
<span>
|
||||
{downloadProgress.filename ||
|
||||
(cudaAvailable
|
||||
? 'Updating CUDA backend...'
|
||||
: 'Downloading CUDA backend...')}
|
||||
</span>
|
||||
</div>
|
||||
{downloadProgress.total > 0 && (
|
||||
<span className="text-muted-foreground">
|
||||
{downloadProgress.progress.toFixed(1)}%
|
||||
</span>
|
||||
)}
|
||||
</div>
|
||||
{downloadProgress.total > 0 && (
|
||||
<>
|
||||
<Progress value={downloadProgress.progress} className="h-2" />
|
||||
<div className="text-xs text-muted-foreground">
|
||||
{formatBytes(downloadProgress.current)} /{' '}
|
||||
{formatBytes(downloadProgress.total)}
|
||||
</div>
|
||||
</>
|
||||
)}
|
||||
{restartPhase !== 'idle' ? (
|
||||
<div className="flex items-center gap-2 p-3 rounded-lg bg-primary/5 border">
|
||||
<Loader2 className="h-4 w-4 animate-spin" />
|
||||
<span className="text-sm">
|
||||
{restartPhase === 'stopping' && 'Stopping server...'}
|
||||
{restartPhase === 'waiting' && 'Restarting server...'}
|
||||
{restartPhase === 'ready' && 'Server restarted successfully!'}
|
||||
</span>
|
||||
</div>
|
||||
) : (
|
||||
<div className="space-y-3">
|
||||
<p className="text-sm text-muted-foreground">
|
||||
Running with ROCm GPU acceleration for AMD. Switch back to CPU if needed (you can
|
||||
re-download later).
|
||||
</p>
|
||||
<Button
|
||||
onClick={handleSwitchToCpuFromRocm}
|
||||
variant="outline"
|
||||
className="w-full"
|
||||
size="sm"
|
||||
>
|
||||
<RotateCw className="h-4 w-4 mr-2" />
|
||||
Switch to CPU Backend
|
||||
</Button>
|
||||
</div>
|
||||
)}
|
||||
{error && (
|
||||
<div className="flex items-center gap-2 text-sm text-destructive">
|
||||
<AlertCircle className="h-4 w-4 shrink-0" />
|
||||
<span>{error}</span>
|
||||
</div>
|
||||
)}
|
||||
</>
|
||||
)}
|
||||
|
||||
{/* Backend download/manage sections - show when no native GPU and not currently running GPU */}
|
||||
{!hasNativeGpu && !isCurrentlyCuda && !isCurrentlyRocm && (
|
||||
<>
|
||||
{/* CUDA Section */}
|
||||
<div className="space-y-4">
|
||||
<div className="text-sm font-medium">NVIDIA (CUDA)</div>
|
||||
|
||||
{/* CUDA Download progress */}
|
||||
{cudaDownloading && downloadProgress && (
|
||||
<div className="space-y-2">
|
||||
<div className="flex items-center justify-between text-sm">
|
||||
<div className="flex items-center gap-2">
|
||||
<Loader2 className="h-4 w-4 animate-spin" />
|
||||
<span>
|
||||
{downloadProgress.filename ||
|
||||
(cudaAvailable
|
||||
? 'Updating CUDA backend...'
|
||||
: 'Downloading CUDA backend...')}
|
||||
</span>
|
||||
</div>
|
||||
{downloadProgress.total > 0 && (
|
||||
<span className="text-muted-foreground">
|
||||
{downloadProgress.progress.toFixed(1)}%
|
||||
</span>
|
||||
)}
|
||||
</div>
|
||||
{downloadProgress.total > 0 && (
|
||||
<>
|
||||
<Progress value={downloadProgress.progress} className="h-2" />
|
||||
<div className="text-xs text-muted-foreground">
|
||||
{formatBytes(downloadProgress.current)} /{' '}
|
||||
{formatBytes(downloadProgress.total)}
|
||||
</div>
|
||||
</>
|
||||
)}
|
||||
</div>
|
||||
)}
|
||||
|
||||
{/* CUDA Actions */}
|
||||
{restartPhase === 'idle' && !cudaDownloading && (
|
||||
<div className="space-y-2">
|
||||
{!cudaAvailable && (
|
||||
<div className="space-y-3">
|
||||
<p className="text-sm text-muted-foreground">
|
||||
Download the CUDA backend (~2.4 GB) for NVIDIA GPU acceleration. Requires an
|
||||
NVIDIA GPU with CUDA support.
|
||||
</p>
|
||||
<Button onClick={handleDownloadCuda} className="w-full" size="sm">
|
||||
<Download className="h-4 w-4 mr-2" />
|
||||
Download CUDA Backend
|
||||
</Button>
|
||||
</div>
|
||||
)}
|
||||
|
||||
{cudaAvailable && platform.metadata.isTauri && (
|
||||
<div className="space-y-3">
|
||||
<p className="text-sm text-muted-foreground">
|
||||
CUDA backend is downloaded and ready. Restart the server to enable GPU
|
||||
acceleration.
|
||||
</p>
|
||||
<Button onClick={handleRestart} className="w-full" size="sm">
|
||||
<RotateCw className="h-4 w-4 mr-2" />
|
||||
Switch to CUDA Backend
|
||||
</Button>
|
||||
</div>
|
||||
)}
|
||||
|
||||
{cudaAvailable && (
|
||||
<Button
|
||||
onClick={handleDeleteCuda}
|
||||
variant="ghost"
|
||||
className="w-full text-muted-foreground hover:text-destructive"
|
||||
size="sm"
|
||||
>
|
||||
<Trash2 className="h-4 w-4 mr-2" />
|
||||
Remove CUDA Backend
|
||||
</Button>
|
||||
)}
|
||||
</div>
|
||||
)}
|
||||
</div>
|
||||
|
||||
{/* Divider */}
|
||||
<div className="border-t" />
|
||||
|
||||
{/* ROCm Section */}
|
||||
<div className="space-y-4">
|
||||
<div className="text-sm font-medium">AMD (ROCm)</div>
|
||||
|
||||
{/* ROCm Download progress */}
|
||||
{rocmDownloading && rocmDownloadProgress && (
|
||||
<div className="space-y-2">
|
||||
<div className="flex items-center justify-between text-sm">
|
||||
<div className="flex items-center gap-2">
|
||||
<Loader2 className="h-4 w-4 animate-spin" />
|
||||
<span>
|
||||
{rocmDownloadProgress.filename ||
|
||||
(rocmAvailable
|
||||
? 'Updating ROCm backend...'
|
||||
: 'Downloading ROCm backend...')}
|
||||
</span>
|
||||
</div>
|
||||
{rocmDownloadProgress.total > 0 && (
|
||||
<span className="text-muted-foreground">
|
||||
{rocmDownloadProgress.progress.toFixed(1)}%
|
||||
</span>
|
||||
)}
|
||||
</div>
|
||||
{rocmDownloadProgress.total > 0 && (
|
||||
<>
|
||||
<Progress value={rocmDownloadProgress.progress} className="h-2" />
|
||||
<div className="text-xs text-muted-foreground">
|
||||
{formatBytes(rocmDownloadProgress.current)} /{' '}
|
||||
{formatBytes(rocmDownloadProgress.total)}
|
||||
</div>
|
||||
</>
|
||||
)}
|
||||
</div>
|
||||
)}
|
||||
|
||||
{/* ROCm Actions */}
|
||||
{restartPhase === 'idle' && !rocmDownloading && (
|
||||
<div className="space-y-2">
|
||||
{!rocmAvailable && (
|
||||
<div className="space-y-3">
|
||||
<p className="text-sm text-muted-foreground">
|
||||
Download the ROCm backend (~2-3 GB) for AMD GPU acceleration. Requires an
|
||||
AMD Radeon GPU with ROCm support.
|
||||
</p>
|
||||
<Button onClick={handleDownloadRocm} className="w-full" size="sm">
|
||||
<Download className="h-4 w-4 mr-2" />
|
||||
Download AMD ROCm Backend
|
||||
</Button>
|
||||
</div>
|
||||
)}
|
||||
|
||||
{rocmAvailable && platform.metadata.isTauri && (
|
||||
<div className="space-y-3">
|
||||
<p className="text-sm text-muted-foreground">
|
||||
ROCm backend is downloaded and ready. Restart the server to enable AMD GPU
|
||||
acceleration.
|
||||
</p>
|
||||
<Button onClick={handleRestart} className="w-full" size="sm">
|
||||
<RotateCw className="h-4 w-4 mr-2" />
|
||||
Switch to ROCm Backend
|
||||
</Button>
|
||||
</div>
|
||||
)}
|
||||
|
||||
{rocmAvailable && (
|
||||
<Button
|
||||
onClick={handleDeleteRocm}
|
||||
variant="ghost"
|
||||
className="w-full text-muted-foreground hover:text-destructive"
|
||||
size="sm"
|
||||
>
|
||||
<Trash2 className="h-4 w-4 mr-2" />
|
||||
Remove ROCm Backend
|
||||
</Button>
|
||||
)}
|
||||
</div>
|
||||
)}
|
||||
</div>
|
||||
|
||||
{/* Restart in progress */}
|
||||
{restartPhase !== 'idle' && (
|
||||
@@ -329,52 +609,6 @@ export function GpuAcceleration() {
|
||||
<span>{error}</span>
|
||||
</div>
|
||||
)}
|
||||
|
||||
{/* Actions */}
|
||||
{restartPhase === 'idle' && !cudaDownloading && (
|
||||
<div className="space-y-2">
|
||||
{/* Not downloaded yet - show download button */}
|
||||
{!cudaAvailable && (
|
||||
<div className="space-y-3">
|
||||
<p className="text-sm text-muted-foreground">
|
||||
Download the CUDA backend (~2.4 GB) for NVIDIA GPU acceleration. Requires an
|
||||
NVIDIA GPU with CUDA support.
|
||||
</p>
|
||||
<Button onClick={handleDownload} className="w-full" size="sm">
|
||||
<Download className="h-4 w-4 mr-2" />
|
||||
Download CUDA Backend
|
||||
</Button>
|
||||
</div>
|
||||
)}
|
||||
|
||||
{/* Downloaded but not active - show switch button */}
|
||||
{cudaAvailable && platform.metadata.isTauri && (
|
||||
<div className="space-y-3">
|
||||
<p className="text-sm text-muted-foreground">
|
||||
CUDA backend is downloaded and ready. Restart the server to enable GPU
|
||||
acceleration.
|
||||
</p>
|
||||
<Button onClick={handleRestart} className="w-full" size="sm">
|
||||
<RotateCw className="h-4 w-4 mr-2" />
|
||||
Switch to CUDA Backend
|
||||
</Button>
|
||||
</div>
|
||||
)}
|
||||
|
||||
{/* Delete option when downloaded (and not active) */}
|
||||
{cudaAvailable && (
|
||||
<Button
|
||||
onClick={handleDelete}
|
||||
variant="ghost"
|
||||
className="w-full text-muted-foreground "
|
||||
size="sm"
|
||||
>
|
||||
<Trash2 className="h-4 w-4 mr-2" />
|
||||
Remove CUDA Backend
|
||||
</Button>
|
||||
)}
|
||||
</div>
|
||||
)}
|
||||
</>
|
||||
)}
|
||||
</CardContent>
|
||||
|
||||
@@ -5,7 +5,7 @@ import { useTranslation } from 'react-i18next';
|
||||
import { Button } from '@/components/ui/button';
|
||||
import { Progress } from '@/components/ui/progress';
|
||||
import { apiClient } from '@/lib/api/client';
|
||||
import type { CudaDownloadProgress, HealthResponse } from '@/lib/api/types';
|
||||
import type { CudaDownloadProgress, RocmDownloadProgress, HealthResponse } from '@/lib/api/types';
|
||||
import { useServerHealth } from '@/lib/hooks/useServer';
|
||||
import { usePlatform } from '@/platform/PlatformContext';
|
||||
import { useServerStore } from '@/stores/serverStore';
|
||||
@@ -50,7 +50,10 @@ function GpuInfoCard({ health }: { health: HealthResponse }) {
|
||||
: null;
|
||||
const gpuBackend = hasGpu ? health.gpu_type!.replace(/\s*\(.+\)$/, '') : null;
|
||||
const isApple = gpuBackend === 'MPS' || gpuBackend === 'Metal';
|
||||
const showBackendVariant = health.backend_variant && health.backend_variant !== 'cpu';
|
||||
const showBackendVariant =
|
||||
health.backend_variant &&
|
||||
health.backend_variant !== 'cpu' &&
|
||||
health.backend_variant.toLowerCase() !== gpuBackend?.toLowerCase();
|
||||
|
||||
return (
|
||||
<div className="rounded-lg border border-border/60 p-4">
|
||||
@@ -115,10 +118,14 @@ export function GpuPage() {
|
||||
|
||||
const [restartPhase, setRestartPhase] = useState<RestartPhase>('idle');
|
||||
const [error, setError] = useState<string | null>(null);
|
||||
const [cudaStreaming, setCudaStreaming] = useState(false);
|
||||
const [rocmStreaming, setRocmStreaming] = useState(false);
|
||||
const [downloadProgress, setDownloadProgress] = useState<CudaDownloadProgress | null>(null);
|
||||
const [rocmDownloadProgress, setRocmDownloadProgress] = useState<RocmDownloadProgress | null>(
|
||||
null,
|
||||
);
|
||||
const healthPollRef = useRef<ReturnType<typeof setInterval> | null>(null);
|
||||
// Hold the latest `t` in a ref so the CUDA progress SSE effect below doesn't
|
||||
// tear down and reconnect the EventSource every time the language changes.
|
||||
|
||||
const tRef = useRef(t);
|
||||
useEffect(() => {
|
||||
tRef.current = t;
|
||||
@@ -136,9 +143,27 @@ export function GpuPage() {
|
||||
enabled: !!health,
|
||||
});
|
||||
|
||||
const {
|
||||
data: rocmStatus,
|
||||
isLoading: _rocmStatusLoading,
|
||||
refetch: refetchRocmStatus,
|
||||
} = useQuery({
|
||||
queryKey: ['rocm-status', serverUrl],
|
||||
queryFn: () => apiClient.getRocmStatus(),
|
||||
refetchInterval: (query) => (query.state.status === 'pending' ? false : 10000),
|
||||
retry: 1,
|
||||
enabled: !!health,
|
||||
});
|
||||
|
||||
const isCurrentlyCuda = health?.backend_variant === 'cuda';
|
||||
const isCurrentlyRocm = health?.backend_variant === 'rocm';
|
||||
const cudaAvailable = cudaStatus?.available ?? false;
|
||||
const cudaDownloading = cudaStatus?.downloading ?? false;
|
||||
const rocmAvailable = rocmStatus?.available ?? false;
|
||||
const rocmDownloading = rocmStatus?.downloading ?? false;
|
||||
// The ROCm backend only applies to AMD GPUs on Windows. Show the section when
|
||||
// the backend detects applicable hardware, or it is already downloaded/active.
|
||||
const supportsRocm = (health?.supports_rocm ?? false) || rocmAvailable || isCurrentlyRocm;
|
||||
|
||||
useEffect(() => {
|
||||
return () => {
|
||||
@@ -150,7 +175,7 @@ export function GpuPage() {
|
||||
}, []);
|
||||
|
||||
useEffect(() => {
|
||||
if (!cudaDownloading || !serverUrl) return;
|
||||
if ((!cudaDownloading && !cudaStreaming) || !serverUrl) return;
|
||||
|
||||
const eventSource = new EventSource(`${serverUrl}/backend/cuda-progress`);
|
||||
|
||||
@@ -162,11 +187,13 @@ export function GpuPage() {
|
||||
if (data.status === 'complete') {
|
||||
eventSource.close();
|
||||
setDownloadProgress(null);
|
||||
setCudaStreaming(false);
|
||||
refetchCudaStatus();
|
||||
} else if (data.status === 'error') {
|
||||
eventSource.close();
|
||||
setError(data.error || tRef.current('settings.gpu.errors.downloadFailed'));
|
||||
setDownloadProgress(null);
|
||||
setCudaStreaming(false);
|
||||
refetchCudaStatus();
|
||||
}
|
||||
} catch (e) {
|
||||
@@ -176,12 +203,50 @@ export function GpuPage() {
|
||||
|
||||
eventSource.onerror = () => {
|
||||
eventSource.close();
|
||||
setCudaStreaming(false);
|
||||
};
|
||||
|
||||
return () => {
|
||||
eventSource.close();
|
||||
};
|
||||
}, [cudaDownloading, serverUrl, refetchCudaStatus]);
|
||||
}, [cudaDownloading, cudaStreaming, serverUrl, refetchCudaStatus]);
|
||||
|
||||
useEffect(() => {
|
||||
if ((!rocmDownloading && !rocmStreaming) || !serverUrl) return;
|
||||
|
||||
const eventSource = new EventSource(`${serverUrl}/backend/rocm-progress`);
|
||||
|
||||
eventSource.onmessage = (event) => {
|
||||
try {
|
||||
const data = JSON.parse(event.data) as RocmDownloadProgress;
|
||||
setRocmDownloadProgress(data);
|
||||
|
||||
if (data.status === 'complete') {
|
||||
eventSource.close();
|
||||
setRocmDownloadProgress(null);
|
||||
setRocmStreaming(false);
|
||||
refetchRocmStatus();
|
||||
} else if (data.status === 'error') {
|
||||
eventSource.close();
|
||||
setError(data.error || tRef.current('settings.gpu.errors.downloadFailed'));
|
||||
setRocmDownloadProgress(null);
|
||||
setRocmStreaming(false);
|
||||
refetchRocmStatus();
|
||||
}
|
||||
} catch (e) {
|
||||
console.error('Error parsing ROCm progress event:', e);
|
||||
}
|
||||
};
|
||||
|
||||
eventSource.onerror = () => {
|
||||
eventSource.close();
|
||||
setRocmStreaming(false);
|
||||
};
|
||||
|
||||
return () => {
|
||||
eventSource.close();
|
||||
};
|
||||
}, [rocmDownloading, rocmStreaming, serverUrl, refetchRocmStatus]);
|
||||
|
||||
const clearHealthPolling = useCallback(() => {
|
||||
if (healthPollRef.current) {
|
||||
@@ -224,10 +289,11 @@ export function GpuPage() {
|
||||
[platform, startHealthPolling, clearHealthPolling],
|
||||
);
|
||||
|
||||
const handleDownload = async () => {
|
||||
const handleDownloadCuda = async () => {
|
||||
setError(null);
|
||||
try {
|
||||
await apiClient.downloadCudaBackend();
|
||||
setCudaStreaming(true);
|
||||
refetchCudaStatus();
|
||||
} catch (e: unknown) {
|
||||
const msg = e instanceof Error ? e.message : t('settings.gpu.errors.downloadStart');
|
||||
@@ -239,28 +305,64 @@ export function GpuPage() {
|
||||
}
|
||||
};
|
||||
|
||||
const handleRestart = async () => {
|
||||
const handleDownloadRocm = async () => {
|
||||
setError(null);
|
||||
try {
|
||||
await restartServerWithPolling(t('settings.gpu.errors.restartFailed'));
|
||||
await apiClient.downloadRocmBackend();
|
||||
setRocmStreaming(true);
|
||||
refetchRocmStatus();
|
||||
} catch (e: unknown) {
|
||||
setError(e instanceof Error ? e.message : t('settings.gpu.errors.restartFailed'));
|
||||
const msg = e instanceof Error ? e.message : t('settings.gpu.errors.downloadStart');
|
||||
if (msg.includes('already downloaded')) {
|
||||
refetchRocmStatus();
|
||||
} else {
|
||||
setError(msg);
|
||||
}
|
||||
}
|
||||
};
|
||||
|
||||
|
||||
const handleSwitchToCpu = async () => {
|
||||
setError(null);
|
||||
setRestartPhase('stopping');
|
||||
try {
|
||||
await apiClient.deleteCudaBackend();
|
||||
await platform.lifecycle.setBackendOverride('cpu');
|
||||
await restartServerWithPolling(t('settings.gpu.errors.switchCpu'));
|
||||
} catch (e: unknown) {
|
||||
setRestartPhase('idle');
|
||||
setError(e instanceof Error ? e.message : t('settings.gpu.errors.switchCpu'));
|
||||
refetchCudaStatus();
|
||||
refetchRocmStatus();
|
||||
}
|
||||
};
|
||||
|
||||
const handleSwitchToCuda = async () => {
|
||||
setError(null);
|
||||
setRestartPhase('stopping');
|
||||
try {
|
||||
await platform.lifecycle.setBackendOverride('cuda');
|
||||
await restartServerWithPolling(t('settings.gpu.errors.restartFailed'));
|
||||
} catch (e: unknown) {
|
||||
setRestartPhase('idle');
|
||||
setError(e instanceof Error ? e.message : t('settings.gpu.errors.restartFailed'));
|
||||
refetchCudaStatus();
|
||||
}
|
||||
};
|
||||
|
||||
const handleDelete = async () => {
|
||||
const handleSwitchToRocm = async () => {
|
||||
setError(null);
|
||||
setRestartPhase('stopping');
|
||||
try {
|
||||
await platform.lifecycle.setBackendOverride('rocm');
|
||||
await restartServerWithPolling(t('settings.gpu.errors.restartFailed'));
|
||||
} catch (e: unknown) {
|
||||
setRestartPhase('idle');
|
||||
setError(e instanceof Error ? e.message : t('settings.gpu.errors.restartFailed'));
|
||||
refetchRocmStatus();
|
||||
}
|
||||
};
|
||||
|
||||
const handleDeleteCuda = async () => {
|
||||
setError(null);
|
||||
try {
|
||||
await apiClient.deleteCudaBackend();
|
||||
@@ -270,6 +372,16 @@ export function GpuPage() {
|
||||
}
|
||||
};
|
||||
|
||||
const handleDeleteRocm = async () => {
|
||||
setError(null);
|
||||
try {
|
||||
await apiClient.deleteRocmBackend();
|
||||
refetchRocmStatus();
|
||||
} catch (e: unknown) {
|
||||
setError(e instanceof Error ? e.message : t('settings.gpu.errors.deleteRocm'));
|
||||
}
|
||||
};
|
||||
|
||||
const formatBytes = (bytes: number): string => {
|
||||
if (bytes === 0) return '0 B';
|
||||
const k = 1024;
|
||||
@@ -283,6 +395,7 @@ export function GpuPage() {
|
||||
const hasNativeGpu =
|
||||
health.gpu_available &&
|
||||
!isCurrentlyCuda &&
|
||||
!isCurrentlyRocm &&
|
||||
health.gpu_type &&
|
||||
!health.gpu_type.includes('CUDA');
|
||||
|
||||
@@ -290,33 +403,188 @@ export function GpuPage() {
|
||||
<div className="space-y-8 max-w-2xl">
|
||||
<GpuInfoCard health={health} />
|
||||
|
||||
{!hasNativeGpu && !isCurrentlyCuda && (
|
||||
<SettingSection
|
||||
title={t('settings.gpu.cuda.title')}
|
||||
description={t('settings.gpu.cuda.description')}
|
||||
>
|
||||
{cudaDownloading && downloadProgress && (
|
||||
<SettingRow title={t('settings.gpu.cuda.downloading')}>
|
||||
<div className="space-y-1.5">
|
||||
<Progress value={downloadProgress.progress} className="h-2" />
|
||||
<div className="flex items-center justify-between text-xs text-muted-foreground">
|
||||
<span>
|
||||
{downloadProgress.filename ||
|
||||
(cudaAvailable
|
||||
? t('settings.gpu.cuda.updating')
|
||||
: t('settings.gpu.cuda.downloadingShort'))}
|
||||
</span>
|
||||
<span>
|
||||
{downloadProgress.total > 0
|
||||
? `${formatBytes(downloadProgress.current)} / ${formatBytes(downloadProgress.total)}`
|
||||
: `${downloadProgress.progress.toFixed(1)}%`}
|
||||
</span>
|
||||
{!hasNativeGpu && !isCurrentlyCuda && !isCurrentlyRocm && (
|
||||
<>
|
||||
<SettingSection
|
||||
title={t('settings.gpu.cuda.title')}
|
||||
description={t('settings.gpu.cuda.description')}
|
||||
>
|
||||
{cudaDownloading && downloadProgress && (
|
||||
<SettingRow title={t('settings.gpu.cuda.downloading')}>
|
||||
<div className="space-y-1.5">
|
||||
<Progress value={downloadProgress.progress} className="h-2" />
|
||||
<div className="flex items-center justify-between text-xs text-muted-foreground">
|
||||
<span>
|
||||
{downloadProgress.filename ||
|
||||
(cudaAvailable
|
||||
? t('settings.gpu.cuda.updating')
|
||||
: t('settings.gpu.cuda.downloadingShort'))}
|
||||
</span>
|
||||
<span>
|
||||
{downloadProgress.total > 0
|
||||
? `${formatBytes(downloadProgress.current)} / ${formatBytes(downloadProgress.total)}`
|
||||
: `${downloadProgress.progress.toFixed(1)}%`}
|
||||
</span>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
</SettingRow>
|
||||
)}
|
||||
</SettingRow>
|
||||
)}
|
||||
|
||||
{restartPhase !== 'idle' && (
|
||||
{restartPhase !== 'idle' && (
|
||||
<SettingRow
|
||||
title={
|
||||
restartPhase === 'ready'
|
||||
? t('settings.gpu.restart.ready')
|
||||
: restartPhase === 'waiting'
|
||||
? t('settings.gpu.restart.waiting')
|
||||
: t('settings.gpu.restart.stopping')
|
||||
}
|
||||
action={<Loader2 className="h-4 w-4 animate-spin text-muted-foreground" />}
|
||||
/>
|
||||
)}
|
||||
|
||||
{error && (
|
||||
<SettingRow title={t('common.error')}>
|
||||
<div className="flex items-center gap-2 text-sm text-destructive">
|
||||
<AlertCircle className="h-4 w-4 shrink-0" />
|
||||
<span>{error}</span>
|
||||
</div>
|
||||
</SettingRow>
|
||||
)}
|
||||
|
||||
{restartPhase === 'idle' && !cudaDownloading && (
|
||||
<>
|
||||
{!cudaAvailable && !isCurrentlyCuda && (
|
||||
<SettingRow
|
||||
title={t('settings.gpu.download.title')}
|
||||
description={t('settings.gpu.download.description')}
|
||||
action={
|
||||
<Button onClick={handleDownloadCuda} size="sm">
|
||||
<Download className="h-3.5 w-3.5 mr-1.5" />
|
||||
{t('settings.gpu.download.button')}
|
||||
</Button>
|
||||
}
|
||||
/>
|
||||
)}
|
||||
|
||||
{cudaAvailable && !isCurrentlyCuda && platform.metadata.isTauri && (
|
||||
<SettingRow
|
||||
title={t('settings.gpu.switchToCuda.title')}
|
||||
description={t('settings.gpu.switchToCuda.description')}
|
||||
action={
|
||||
<Button onClick={handleSwitchToCuda} size="sm">
|
||||
<RotateCw className="h-3.5 w-3.5 mr-1.5" />
|
||||
{t('settings.gpu.switchToCuda.button')}
|
||||
</Button>
|
||||
}
|
||||
/>
|
||||
)}
|
||||
|
||||
{cudaAvailable && !isCurrentlyCuda && (
|
||||
<SettingRow
|
||||
title={t('settings.gpu.remove.title')}
|
||||
description={t('settings.gpu.remove.description')}
|
||||
action={
|
||||
<Button
|
||||
onClick={handleDeleteCuda}
|
||||
variant="ghost"
|
||||
size="sm"
|
||||
className="text-muted-foreground hover:text-destructive"
|
||||
>
|
||||
<Trash2 className="h-3.5 w-3.5 mr-1.5" />
|
||||
{t('settings.gpu.remove.button')}
|
||||
</Button>
|
||||
}
|
||||
/>
|
||||
)}
|
||||
</>
|
||||
)}
|
||||
</SettingSection>
|
||||
|
||||
{supportsRocm && (
|
||||
<SettingSection
|
||||
title={t('settings.gpu.rocm.title')}
|
||||
description={t('settings.gpu.rocm.description')}
|
||||
>
|
||||
{rocmDownloading && rocmDownloadProgress && (
|
||||
<SettingRow title={t('settings.gpu.rocm.downloading')}>
|
||||
<div className="space-y-1.5">
|
||||
<Progress value={rocmDownloadProgress.progress} className="h-2" />
|
||||
<div className="flex items-center justify-between text-xs text-muted-foreground">
|
||||
<span>
|
||||
{rocmDownloadProgress.filename ||
|
||||
(rocmAvailable
|
||||
? t('settings.gpu.rocm.updating')
|
||||
: t('settings.gpu.rocm.downloadingShort'))}
|
||||
</span>
|
||||
<span>
|
||||
{rocmDownloadProgress.total > 0
|
||||
? `${formatBytes(rocmDownloadProgress.current)} / ${formatBytes(rocmDownloadProgress.total)}`
|
||||
: `${rocmDownloadProgress.progress.toFixed(1)}%`}
|
||||
</span>
|
||||
</div>
|
||||
</div>
|
||||
</SettingRow>
|
||||
)}
|
||||
|
||||
{restartPhase === 'idle' && !rocmDownloading && (
|
||||
<>
|
||||
{!rocmAvailable && !isCurrentlyRocm && (
|
||||
<SettingRow
|
||||
title={t('settings.gpu.downloadRocm.title')}
|
||||
description={t('settings.gpu.downloadRocm.description')}
|
||||
action={
|
||||
<Button onClick={handleDownloadRocm} size="sm">
|
||||
<Download className="h-3.5 w-3.5 mr-1.5" />
|
||||
{t('settings.gpu.downloadRocm.button')}
|
||||
</Button>
|
||||
}
|
||||
/>
|
||||
)}
|
||||
|
||||
{rocmAvailable && !isCurrentlyRocm && platform.metadata.isTauri && (
|
||||
<SettingRow
|
||||
title={t('settings.gpu.switchToRocm.title')}
|
||||
description={t('settings.gpu.switchToRocm.description')}
|
||||
action={
|
||||
<Button onClick={handleSwitchToRocm} size="sm">
|
||||
<RotateCw className="h-3.5 w-3.5 mr-1.5" />
|
||||
{t('settings.gpu.switchToRocm.button')}
|
||||
</Button>
|
||||
}
|
||||
/>
|
||||
)}
|
||||
|
||||
{rocmAvailable && !isCurrentlyRocm && (
|
||||
<SettingRow
|
||||
title={t('settings.gpu.removeRocm.title')}
|
||||
description={t('settings.gpu.removeRocm.description')}
|
||||
action={
|
||||
<Button
|
||||
onClick={handleDeleteRocm}
|
||||
variant="ghost"
|
||||
size="sm"
|
||||
className="text-muted-foreground hover:text-destructive"
|
||||
>
|
||||
<Trash2 className="h-3.5 w-3.5 mr-1.5" />
|
||||
{t('settings.gpu.removeRocm.button')}
|
||||
</Button>
|
||||
}
|
||||
/>
|
||||
)}
|
||||
</>
|
||||
)}
|
||||
</SettingSection>
|
||||
)}
|
||||
</>
|
||||
)}
|
||||
|
||||
{(isCurrentlyCuda || isCurrentlyRocm) && platform.metadata.isTauri && (
|
||||
<SettingSection
|
||||
title={isCurrentlyCuda ? t('settings.gpu.cuda.activeTitle') : t('settings.gpu.rocm.activeTitle')}
|
||||
description={t('settings.gpu.activeBackend.description')}
|
||||
>
|
||||
{restartPhase !== 'idle' ? (
|
||||
<SettingRow
|
||||
title={
|
||||
restartPhase === 'ready'
|
||||
@@ -327,8 +595,18 @@ export function GpuPage() {
|
||||
}
|
||||
action={<Loader2 className="h-4 w-4 animate-spin text-muted-foreground" />}
|
||||
/>
|
||||
) : (
|
||||
<SettingRow
|
||||
title={t('settings.gpu.switchToCpu.title')}
|
||||
description={t('settings.gpu.switchToCpu.description')}
|
||||
action={
|
||||
<Button onClick={handleSwitchToCpu} variant="outline" size="sm">
|
||||
<RotateCw className="h-3.5 w-3.5 mr-1.5" />
|
||||
{t('settings.gpu.switchToCpu.button')}
|
||||
</Button>
|
||||
}
|
||||
/>
|
||||
)}
|
||||
|
||||
{error && (
|
||||
<SettingRow title={t('common.error')}>
|
||||
<div className="flex items-center gap-2 text-sm text-destructive">
|
||||
@@ -337,67 +615,6 @@ export function GpuPage() {
|
||||
</div>
|
||||
</SettingRow>
|
||||
)}
|
||||
|
||||
{restartPhase === 'idle' && !cudaDownloading && (
|
||||
<>
|
||||
{!cudaAvailable && !isCurrentlyCuda && (
|
||||
<SettingRow
|
||||
title={t('settings.gpu.download.title')}
|
||||
description={t('settings.gpu.download.description')}
|
||||
action={
|
||||
<Button onClick={handleDownload} size="sm">
|
||||
<Download className="h-3.5 w-3.5 mr-1.5" />
|
||||
{t('settings.gpu.download.button')}
|
||||
</Button>
|
||||
}
|
||||
/>
|
||||
)}
|
||||
|
||||
{cudaAvailable && !isCurrentlyCuda && platform.metadata.isTauri && (
|
||||
<SettingRow
|
||||
title={t('settings.gpu.switchToCuda.title')}
|
||||
description={t('settings.gpu.switchToCuda.description')}
|
||||
action={
|
||||
<Button onClick={handleRestart} size="sm">
|
||||
<RotateCw className="h-3.5 w-3.5 mr-1.5" />
|
||||
{t('settings.gpu.switchToCuda.button')}
|
||||
</Button>
|
||||
}
|
||||
/>
|
||||
)}
|
||||
|
||||
{isCurrentlyCuda && platform.metadata.isTauri && (
|
||||
<SettingRow
|
||||
title={t('settings.gpu.switchToCpu.title')}
|
||||
description={t('settings.gpu.switchToCpu.description')}
|
||||
action={
|
||||
<Button onClick={handleSwitchToCpu} variant="outline" size="sm">
|
||||
<RotateCw className="h-3.5 w-3.5 mr-1.5" />
|
||||
{t('settings.gpu.switchToCpu.button')}
|
||||
</Button>
|
||||
}
|
||||
/>
|
||||
)}
|
||||
|
||||
{cudaAvailable && !isCurrentlyCuda && (
|
||||
<SettingRow
|
||||
title={t('settings.gpu.remove.title')}
|
||||
description={t('settings.gpu.remove.description')}
|
||||
action={
|
||||
<Button
|
||||
onClick={handleDelete}
|
||||
variant="ghost"
|
||||
size="sm"
|
||||
className="text-muted-foreground "
|
||||
>
|
||||
<Trash2 className="h-3.5 w-3.5 mr-1.5" />
|
||||
{t('settings.gpu.remove.button')}
|
||||
</Button>
|
||||
}
|
||||
/>
|
||||
)}
|
||||
</>
|
||||
)}
|
||||
</SettingSection>
|
||||
)}
|
||||
|
||||
|
||||
@@ -760,8 +760,13 @@
|
||||
}
|
||||
},
|
||||
"general": {
|
||||
"docs": { "title": "Read the Docs" },
|
||||
"discord": { "title": "Join the Discord", "subtitle": "Get help & share voices" },
|
||||
"docs": {
|
||||
"title": "Read the Docs"
|
||||
},
|
||||
"discord": {
|
||||
"title": "Join the Discord",
|
||||
"subtitle": "Get help & share voices"
|
||||
},
|
||||
"serverUrl": {
|
||||
"title": "Server URL",
|
||||
"description": "The address of your voicebox backend server.",
|
||||
@@ -1091,11 +1096,15 @@
|
||||
"active": "Active",
|
||||
"cuda": {
|
||||
"title": "CUDA Backend",
|
||||
"activeTitle": "CUDA Backend Active",
|
||||
"description": "NVIDIA GPU acceleration via a downloadable CUDA backend.",
|
||||
"downloading": "Downloading CUDA backend…",
|
||||
"downloadingShort": "Downloading…",
|
||||
"updating": "Updating…"
|
||||
},
|
||||
"activeBackend": {
|
||||
"description": "GPU acceleration is currently enabled."
|
||||
},
|
||||
"restart": {
|
||||
"ready": "Server restarted successfully",
|
||||
"waiting": "Restarting server…",
|
||||
@@ -1113,10 +1122,9 @@
|
||||
},
|
||||
"switchToCpu": {
|
||||
"title": "Switch to CPU backend",
|
||||
"description": "Disable GPU acceleration. You can re-download CUDA later.",
|
||||
"description": "Disable GPU acceleration. You can re-download the GPU backend later.",
|
||||
"button": "Switch"
|
||||
},
|
||||
"remove": {
|
||||
}, "remove": {
|
||||
"title": "Remove CUDA backend",
|
||||
"description": "Delete the downloaded CUDA binary to free disk space.",
|
||||
"button": "Remove"
|
||||
@@ -1126,9 +1134,33 @@
|
||||
"downloadStart": "Failed to start download",
|
||||
"restartFailed": "Restart failed",
|
||||
"switchCpu": "Failed to switch to CPU",
|
||||
"deleteCuda": "Failed to delete CUDA backend"
|
||||
"deleteCuda": "Failed to delete CUDA backend",
|
||||
"deleteRocm": "Failed to delete ROCm backend"
|
||||
},
|
||||
"footer": "Voicebox automatically detects and uses the best available GPU on your system. On Apple Silicon Macs, the MLX backend runs natively on the Neural Engine and GPU via Metal Performance Shaders (MPS), with no additional setup required. On Windows and Linux with NVIDIA GPUs, you can download an optional CUDA backend for hardware-accelerated inference. AMD ROCm, Intel XPU, and DirectML are also supported where available through PyTorch. When no GPU is detected, Voicebox falls back to CPU — all engines still work, just slower."
|
||||
"footer": "Voicebox automatically detects and uses the best available GPU on your system. On Apple Silicon Macs, the MLX backend runs natively on the Neural Engine and GPU via Metal Performance Shaders (MPS), with no additional setup required. On Windows, you can download optional CUDA (NVIDIA) or ROCm (AMD) backends for hardware-accelerated inference. Intel XPU and DirectML are also supported where available through PyTorch. When no GPU is detected, Voicebox falls back to CPU — all engines still work, just slower.",
|
||||
"rocm": {
|
||||
"title": "AMD ROCm Backend",
|
||||
"activeTitle": "ROCm Backend Active",
|
||||
"description": "AMD GPU acceleration via a downloadable ROCm backend.",
|
||||
"downloading": "Downloading ROCm backend…",
|
||||
"downloadingShort": "Downloading…",
|
||||
"updating": "Updating…"
|
||||
},
|
||||
"downloadRocm": {
|
||||
"title": "Download AMD ROCm backend",
|
||||
"description": "~2-3 GB download. Requires an AMD Radeon GPU with ROCm support.",
|
||||
"button": "Download"
|
||||
},
|
||||
"switchToRocm": {
|
||||
"title": "Switch to ROCm backend",
|
||||
"description": "ROCm backend is downloaded and ready. Restart to enable.",
|
||||
"button": "Restart"
|
||||
},
|
||||
"removeRocm": {
|
||||
"title": "Remove ROCm backend",
|
||||
"description": "Delete the downloaded ROCm binary to free disk space.",
|
||||
"button": "Remove"
|
||||
}
|
||||
},
|
||||
"logs": {
|
||||
"title": "Server Logs",
|
||||
|
||||
@@ -20,6 +20,7 @@ import type {
|
||||
PresetVoice,
|
||||
PersonalityTextResponse,
|
||||
ProfileSampleResponse,
|
||||
RocmStatus,
|
||||
StoryCreate,
|
||||
StoryDetailResponse,
|
||||
StoryItemBatchUpdate,
|
||||
@@ -693,6 +694,23 @@ class ApiClient {
|
||||
});
|
||||
}
|
||||
|
||||
// ROCm Backend Management
|
||||
async getRocmStatus(): Promise<RocmStatus> {
|
||||
return this.request<RocmStatus>('/backend/rocm-status');
|
||||
}
|
||||
|
||||
async downloadRocmBackend(): Promise<{ message: string; progress_key: string }> {
|
||||
return this.request<{ message: string; progress_key: string }>('/backend/download-rocm', {
|
||||
method: 'POST',
|
||||
});
|
||||
}
|
||||
|
||||
async deleteRocmBackend(): Promise<{ message: string }> {
|
||||
return this.request<{ message: string }>('/backend/rocm', {
|
||||
method: 'DELETE',
|
||||
});
|
||||
}
|
||||
|
||||
// Stories
|
||||
async listStories(): Promise<StoryResponse[]> {
|
||||
return this.request<StoryResponse[]>('/stories');
|
||||
|
||||
@@ -9,7 +9,7 @@ export type ModelStatus = {
|
||||
model_name: string;
|
||||
display_name: string;
|
||||
downloaded: boolean;
|
||||
downloading?: boolean; // True if download is in progress
|
||||
downloading?: boolean; // True if download is in progress
|
||||
size_mb?: number | null;
|
||||
loaded?: boolean;
|
||||
};
|
||||
|
||||
@@ -269,7 +269,8 @@ export interface HealthResponse {
|
||||
gpu_type?: string;
|
||||
vram_used_mb?: number;
|
||||
backend_type?: string;
|
||||
backend_variant?: string; // "cpu" or "cuda"
|
||||
backend_variant?: string; // "cpu", "cuda", or "rocm"
|
||||
supports_rocm?: boolean; // AMD GPU on Windows — the ROCm backend is applicable
|
||||
}
|
||||
|
||||
export interface CudaDownloadProgress {
|
||||
@@ -291,6 +292,26 @@ export interface CudaStatus {
|
||||
download_progress?: CudaDownloadProgress;
|
||||
}
|
||||
|
||||
export interface RocmDownloadProgress {
|
||||
model_name: string;
|
||||
current: number;
|
||||
total: number;
|
||||
progress: number;
|
||||
filename?: string;
|
||||
status: 'downloading' | 'extracting' | 'complete' | 'error';
|
||||
timestamp: string;
|
||||
error?: string;
|
||||
}
|
||||
|
||||
export interface RocmStatus {
|
||||
available: boolean; // ROCm binary exists on disk
|
||||
active: boolean; // Currently running the ROCm binary
|
||||
binary_path?: string;
|
||||
rocm_libs_version?: string;
|
||||
downloading: boolean; // Download in progress
|
||||
download_progress?: RocmDownloadProgress;
|
||||
}
|
||||
|
||||
export interface ModelProgress {
|
||||
model_name: string;
|
||||
current: number;
|
||||
|
||||
@@ -60,6 +60,7 @@ export interface PlatformLifecycle {
|
||||
stopServer(): Promise<void>;
|
||||
restartServer(modelsDir?: string | null): Promise<string>;
|
||||
setKeepServerRunning(keep: boolean): Promise<void>;
|
||||
setBackendOverride(backend?: string | null): Promise<void>;
|
||||
setupWindowCloseHandler(): Promise<void>;
|
||||
subscribeToServerLogs(callback: (entry: ServerLogEntry) => void): () => void;
|
||||
onServerReady?: () => void;
|
||||
|
||||
@@ -326,8 +326,10 @@ async def _run_startup(application: FastAPI) -> None:
|
||||
logger.warning("GPU COMPATIBILITY: %s", _cuda_warning)
|
||||
|
||||
from .services.cuda import check_and_update_cuda_binary
|
||||
from .services.rocm import check_and_update_rocm_binary
|
||||
|
||||
create_background_task(check_and_update_cuda_binary())
|
||||
create_background_task(check_and_update_rocm_binary())
|
||||
|
||||
try:
|
||||
progress_manager = get_progress_manager()
|
||||
|
||||
@@ -138,6 +138,11 @@ def check_cuda_compatibility() -> tuple[bool, str | None]:
|
||||
if not torch.cuda.is_available():
|
||||
return True, None
|
||||
|
||||
# ROCm/HIP uses the cuda frontend but has different architecture names (gfx*).
|
||||
# Skip NVIDIA-specific compute capability checks on AMD hardware.
|
||||
if hasattr(torch.version, "hip") and torch.version.hip:
|
||||
return True, None
|
||||
|
||||
major, minor = torch.cuda.get_device_capability(0)
|
||||
capability = f"{major}.{minor}"
|
||||
device_name = torch.cuda.get_device_name(0)
|
||||
|
||||
@@ -146,7 +146,15 @@ class HumeTadaBackend:
|
||||
)
|
||||
|
||||
# Determine dtype — use bf16 on CUDA/XPU for ~50% memory savings
|
||||
if device == "cuda" and torch.cuda.is_bf16_supported():
|
||||
# On ROCm/AMD, torch.cuda.is_bf16_supported() works via the HIP abstraction,
|
||||
# but we wrap it defensively in case an older build lacks the symbol.
|
||||
_bf16_ok = False
|
||||
if device == "cuda":
|
||||
try:
|
||||
_bf16_ok = torch.cuda.is_bf16_supported()
|
||||
except Exception:
|
||||
_bf16_ok = False
|
||||
if _bf16_ok:
|
||||
model_dtype = torch.bfloat16
|
||||
elif device == "xpu":
|
||||
# Intel Arc (Alchemist+) supports bf16 natively
|
||||
|
||||
+249
-54
@@ -22,24 +22,34 @@ def is_apple_silicon():
|
||||
return platform.system() == "Darwin" and platform.machine() == "arm64"
|
||||
|
||||
|
||||
def build_server(cuda=False):
|
||||
def build_server(cuda=False, rocm=False):
|
||||
"""Build Python server as standalone binary.
|
||||
|
||||
Args:
|
||||
cuda: If True, build with CUDA support and name the binary
|
||||
voicebox-server-cuda instead of voicebox-server.
|
||||
rocm: If True, build with ROCm support and name the binary
|
||||
voicebox-server-rocm instead of voicebox-server.
|
||||
"""
|
||||
if cuda and rocm:
|
||||
raise ValueError("Cannot build with both CUDA and ROCm support")
|
||||
|
||||
backend_dir = Path(__file__).parent
|
||||
|
||||
binary_name = "voicebox-server-cuda" if cuda else "voicebox-server"
|
||||
if rocm:
|
||||
binary_name = "voicebox-server-rocm"
|
||||
elif cuda:
|
||||
binary_name = "voicebox-server-cuda"
|
||||
else:
|
||||
binary_name = "voicebox-server"
|
||||
|
||||
# PyInstaller arguments
|
||||
# CUDA builds use --onedir so we can split the output into two archives:
|
||||
# CUDA and ROCm builds use --onedir so we can split the output into two archives:
|
||||
# 1. Server core (~200-400MB) — versioned with the app
|
||||
# 2. CUDA libs (~2GB) — versioned independently (only redownloaded on
|
||||
# CUDA toolkit / torch major version changes)
|
||||
# 2. GPU libs (~2GB) — versioned independently (only redownloaded on
|
||||
# GPU toolkit / torch major version changes)
|
||||
# CPU builds remain --onefile for simplicity.
|
||||
pack_mode = "--onedir" if cuda else "--onefile"
|
||||
pack_mode = "--onedir" if (cuda or rocm) else "--onefile"
|
||||
args = [
|
||||
"server.py", # Use server.py as entry point instead of main.py
|
||||
pack_mode,
|
||||
@@ -320,22 +330,74 @@ def build_server(cuda=False):
|
||||
]
|
||||
)
|
||||
|
||||
# Add CUDA-specific hidden imports
|
||||
if cuda:
|
||||
logger.info("Building with CUDA support")
|
||||
# Add CUDA/ROCm-specific hidden imports
|
||||
if cuda or rocm:
|
||||
variant = "ROCm" if rocm else "CUDA"
|
||||
logger.info("Building with %s support", variant)
|
||||
gpu_hidden = [
|
||||
"--hidden-import",
|
||||
"torch.cuda",
|
||||
]
|
||||
# cudnn is NVIDIA-specific; ROCm uses MIOpen under the abstraction layer
|
||||
if cuda:
|
||||
gpu_hidden.extend(
|
||||
[
|
||||
"--hidden-import",
|
||||
"torch.backends.cudnn",
|
||||
]
|
||||
)
|
||||
args.extend(gpu_hidden)
|
||||
|
||||
if rocm:
|
||||
# rocm_sdk imports its backend packages dynamically via
|
||||
# importlib.import_module(py_package_name), which PyInstaller's
|
||||
# static analyzer cannot see. We must collect them explicitly —
|
||||
# otherwise only the pure-python rocm_sdk wrapper ships and
|
||||
# rocm_sdk.find_libraries crashes with UnboundLocalError at boot.
|
||||
#
|
||||
# The backend packages also contain the HIP/MIOpen/hipBLAS DLLs
|
||||
# under bin/ (plus ~750 MB of tensile kernel files under
|
||||
# bin/rocblas/library and bin/hipblaslt/library) — collect-all
|
||||
# walks the tree recursively so both DLLs and kernel data are
|
||||
# bundled. See rocm_sdk/_dist_info.py for the package mapping.
|
||||
args.extend(
|
||||
[
|
||||
"--collect-all",
|
||||
"rocm_sdk",
|
||||
"--collect-all",
|
||||
"_rocm_sdk_core",
|
||||
"--collect-all",
|
||||
"_rocm_sdk_libraries_custom",
|
||||
"--collect-all",
|
||||
"rocm_sdk_core",
|
||||
"--collect-all",
|
||||
"rocm_sdk_libraries_custom",
|
||||
"--hidden-import",
|
||||
"torch.cuda",
|
||||
"_rocm_sdk_core",
|
||||
"--hidden-import",
|
||||
"torch.backends.cudnn",
|
||||
"_rocm_sdk_libraries_custom",
|
||||
"--hidden-import",
|
||||
"rocm_sdk_core",
|
||||
"--hidden-import",
|
||||
"rocm_sdk_libraries_custom",
|
||||
"--copy-metadata",
|
||||
"rocm",
|
||||
"--copy-metadata",
|
||||
"rocm-sdk-core",
|
||||
"--copy-metadata",
|
||||
"rocm-sdk-libraries-custom",
|
||||
# Repair rocm_sdk.find_libraries (masks UnboundLocalError
|
||||
# with a readable ModuleNotFoundError on missing backends).
|
||||
"--runtime-hook",
|
||||
"pyi_rth_rocm_sdk.py",
|
||||
]
|
||||
)
|
||||
else:
|
||||
# Exclude NVIDIA CUDA packages from CPU-only builds to keep binary small.
|
||||
# When building from a venv with CUDA torch installed, PyInstaller would
|
||||
# bundle ~3GB of NVIDIA shared libraries. We exclude both the Python
|
||||
# modules and the binary DLLs.
|
||||
|
||||
# Exclude NVIDIA CUDA packages from non-CUDA builds to keep binary small.
|
||||
# When building from a venv with CUDA torch installed, PyInstaller would
|
||||
# bundle ~3GB of NVIDIA shared libraries. We exclude both the Python
|
||||
# modules and the binary DLLs. This applies to CPU and ROCm builds.
|
||||
if not cuda:
|
||||
nvidia_packages = [
|
||||
"nvidia",
|
||||
"nvidia.cublas",
|
||||
@@ -354,8 +416,8 @@ def build_server(cuda=False):
|
||||
for pkg in nvidia_packages:
|
||||
args.extend(["--exclude-module", pkg])
|
||||
|
||||
# Add MLX-specific imports if building on Apple Silicon (never for CUDA builds)
|
||||
if is_apple_silicon() and not cuda:
|
||||
# Add MLX-specific imports if building on Apple Silicon (never for GPU builds)
|
||||
if is_apple_silicon() and not cuda and not rocm:
|
||||
logger.info("Building for Apple Silicon - including MLX dependencies")
|
||||
args.extend(
|
||||
[
|
||||
@@ -399,7 +461,7 @@ def build_server(cuda=False):
|
||||
"mlx_lm",
|
||||
]
|
||||
)
|
||||
elif not cuda:
|
||||
elif not cuda and not rocm:
|
||||
logger.info("Building for non-Apple Silicon platform - PyTorch only")
|
||||
|
||||
dist_dir = str(backend_dir / "dist")
|
||||
@@ -420,43 +482,128 @@ def build_server(cuda=False):
|
||||
os.chdir(backend_dir)
|
||||
|
||||
# For CPU builds on Windows, ensure we're using CPU-only torch.
|
||||
# If CUDA torch is installed (local dev), swap to CPU torch before building,
|
||||
# then restore CUDA torch after. This prevents PyInstaller from bundling
|
||||
# ~3GB of CUDA DLLs into the CPU binary.
|
||||
restore_cuda = False
|
||||
if not cuda and platform.system() == "Windows":
|
||||
import subprocess
|
||||
|
||||
result = subprocess.run(
|
||||
[sys.executable, "-c", "import torch; print(torch.version.cuda or '')"], capture_output=True, text=True
|
||||
)
|
||||
has_cuda_torch = bool(result.stdout.strip())
|
||||
if has_cuda_torch:
|
||||
logger.info("CUDA torch detected — installing CPU torch for CPU build...")
|
||||
subprocess.run(
|
||||
[
|
||||
sys.executable,
|
||||
"-m",
|
||||
"pip",
|
||||
"install",
|
||||
"torch",
|
||||
"torchvision",
|
||||
"torchaudio",
|
||||
"--index-url",
|
||||
"https://download.pytorch.org/whl/cpu",
|
||||
"--force-reinstall",
|
||||
"-q",
|
||||
],
|
||||
check=True,
|
||||
)
|
||||
restore_cuda = True
|
||||
|
||||
# Run PyInstaller
|
||||
# If CUDA or ROCm torch is installed (local dev), swap to CPU torch before
|
||||
# building, then restore afterwards. This prevents PyInstaller from bundling
|
||||
# GPU libraries into the CPU binary.
|
||||
restore_torch = None
|
||||
try:
|
||||
if not cuda and not rocm and platform.system() == "Windows":
|
||||
import subprocess
|
||||
|
||||
cuda_result = subprocess.run(
|
||||
[sys.executable, "-c", "import torch; print(torch.version.cuda or '')"], capture_output=True, text=True
|
||||
)
|
||||
rocm_result = subprocess.run(
|
||||
[sys.executable, "-c", "import torch; print(torch.version.hip or '')"], capture_output=True, text=True
|
||||
)
|
||||
|
||||
if cuda_result.stdout.strip():
|
||||
restore_torch = "cuda"
|
||||
logger.info("CUDA torch detected — installing CPU torch for CPU build...")
|
||||
subprocess.run(
|
||||
[
|
||||
sys.executable,
|
||||
"-m",
|
||||
"pip",
|
||||
"install",
|
||||
"torch",
|
||||
"torchvision",
|
||||
"torchaudio",
|
||||
"--index-url",
|
||||
"https://download.pytorch.org/whl/cpu",
|
||||
"--force-reinstall",
|
||||
"--no-deps",
|
||||
"-q",
|
||||
],
|
||||
check=True,
|
||||
)
|
||||
elif rocm_result.stdout.strip():
|
||||
restore_torch = "rocm"
|
||||
logger.info("ROCm torch detected — installing CPU torch for CPU build...")
|
||||
subprocess.run(
|
||||
[
|
||||
sys.executable,
|
||||
"-m",
|
||||
"pip",
|
||||
"install",
|
||||
"torch",
|
||||
"torchvision",
|
||||
"torchaudio",
|
||||
"--index-url",
|
||||
"https://download.pytorch.org/whl/cpu",
|
||||
"--force-reinstall",
|
||||
"--no-deps",
|
||||
"-q",
|
||||
],
|
||||
check=True,
|
||||
)
|
||||
|
||||
# For ROCm builds on Windows, ensure ROCm torch is installed.
|
||||
if rocm and platform.system() == "Windows":
|
||||
import subprocess
|
||||
|
||||
if sys.implementation.name != "cpython" or sys.version_info[:2] != (3, 12):
|
||||
raise RuntimeError(
|
||||
"ROCm wheels are cp312-cp312-specific; "
|
||||
f"got {sys.implementation.name} {sys.version.split()[0]}. "
|
||||
"Use CPython 3.12 to build the ROCm binary."
|
||||
)
|
||||
|
||||
result = subprocess.run(
|
||||
[sys.executable, "-c", "import torch; print(torch.version.hip or '')"], capture_output=True, text=True
|
||||
)
|
||||
has_rocm_torch = bool(result.stdout.strip())
|
||||
if not has_rocm_torch:
|
||||
logger.info("ROCm torch not detected — installing ROCm torch for ROCm build...")
|
||||
|
||||
# Determine what to restore BEFORE overwriting the environment
|
||||
cuda_result = subprocess.run(
|
||||
[sys.executable, "-c", "import torch; print(torch.version.cuda or '')"],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
)
|
||||
if cuda_result.stdout.strip():
|
||||
restore_torch = "cuda"
|
||||
else:
|
||||
restore_torch = "cpu"
|
||||
|
||||
# Now overwrite the environment safely
|
||||
subprocess.run(
|
||||
[
|
||||
sys.executable,
|
||||
"-m",
|
||||
"pip",
|
||||
"install",
|
||||
"https://repo.radeon.com/rocm/windows/rocm-rel-7.2.1/rocm_sdk_core-7.2.1-py3-none-win_amd64.whl",
|
||||
"https://repo.radeon.com/rocm/windows/rocm-rel-7.2.1/rocm_sdk_devel-7.2.1-py3-none-win_amd64.whl",
|
||||
"https://repo.radeon.com/rocm/windows/rocm-rel-7.2.1/rocm_sdk_libraries_custom-7.2.1-py3-none-win_amd64.whl",
|
||||
"https://repo.radeon.com/rocm/windows/rocm-rel-7.2.1/rocm-7.2.1.tar.gz",
|
||||
"--no-deps",
|
||||
"-q",
|
||||
],
|
||||
check=True,
|
||||
)
|
||||
subprocess.run(
|
||||
[
|
||||
sys.executable,
|
||||
"-m",
|
||||
"pip",
|
||||
"install",
|
||||
"https://repo.radeon.com/rocm/windows/rocm-rel-7.2.1/torch-2.9.1%2Brocm7.2.1-cp312-cp312-win_amd64.whl",
|
||||
"https://repo.radeon.com/rocm/windows/rocm-rel-7.2.1/torchaudio-2.9.1%2Brocm7.2.1-cp312-cp312-win_amd64.whl",
|
||||
"https://repo.radeon.com/rocm/windows/rocm-rel-7.2.1/torchvision-0.24.1%2Brocm7.2.1-cp312-cp312-win_amd64.whl",
|
||||
"--force-reinstall",
|
||||
"--no-deps",
|
||||
"-q",
|
||||
],
|
||||
check=True,
|
||||
)
|
||||
|
||||
# Run PyInstaller
|
||||
PyInstaller.__main__.run(args)
|
||||
finally:
|
||||
# Restore CUDA torch if we swapped it out (even on build failure)
|
||||
if restore_cuda:
|
||||
# Restore torch if we swapped it out (even on build failure)
|
||||
if restore_torch == "cuda":
|
||||
logger.info("Restoring CUDA torch...")
|
||||
import subprocess
|
||||
|
||||
@@ -472,10 +619,52 @@ def build_server(cuda=False):
|
||||
"--index-url",
|
||||
"https://download.pytorch.org/whl/cu128",
|
||||
"--force-reinstall",
|
||||
"--no-deps",
|
||||
"-q",
|
||||
],
|
||||
check=True,
|
||||
)
|
||||
elif restore_torch == "rocm":
|
||||
logger.info("Restoring ROCm torch...")
|
||||
import subprocess
|
||||
|
||||
subprocess.run(
|
||||
[
|
||||
sys.executable,
|
||||
"-m",
|
||||
"pip",
|
||||
"install",
|
||||
"https://repo.radeon.com/rocm/windows/rocm-rel-7.2.1/torch-2.9.1%2Brocm7.2.1-cp312-cp312-win_amd64.whl",
|
||||
"https://repo.radeon.com/rocm/windows/rocm-rel-7.2.1/torchaudio-2.9.1%2Brocm7.2.1-cp312-cp312-win_amd64.whl",
|
||||
"https://repo.radeon.com/rocm/windows/rocm-rel-7.2.1/torchvision-0.24.1%2Brocm7.2.1-cp312-cp312-win_amd64.whl",
|
||||
"--force-reinstall",
|
||||
"--no-deps",
|
||||
"-q",
|
||||
],
|
||||
check=True,
|
||||
)
|
||||
elif restore_torch == "cpu":
|
||||
logger.info("Restoring CPU torch...")
|
||||
import subprocess
|
||||
|
||||
subprocess.run(
|
||||
[
|
||||
sys.executable,
|
||||
"-m",
|
||||
"pip",
|
||||
"install",
|
||||
"torch",
|
||||
"torchvision",
|
||||
"torchaudio",
|
||||
"--index-url",
|
||||
"https://download.pytorch.org/whl/cpu",
|
||||
"--force-reinstall",
|
||||
"--no-deps",
|
||||
"-q",
|
||||
],
|
||||
check=True,
|
||||
)
|
||||
|
||||
|
||||
logger.info("Binary built in %s", backend_dir / "dist" / binary_name)
|
||||
|
||||
@@ -577,6 +766,11 @@ if __name__ == "__main__":
|
||||
action="store_true",
|
||||
help="Build CUDA-enabled binary (voicebox-server-cuda)",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--rocm",
|
||||
action="store_true",
|
||||
help="Build ROCm-enabled binary (voicebox-server-rocm) for AMD GPUs",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--shim",
|
||||
action="store_true",
|
||||
@@ -586,4 +780,5 @@ if __name__ == "__main__":
|
||||
if cli_args.shim:
|
||||
build_shim()
|
||||
else:
|
||||
build_server(cuda=cli_args.cuda)
|
||||
build_server(cuda=cli_args.cuda, rocm=cli_args.rocm)
|
||||
|
||||
|
||||
+2
-1
@@ -442,7 +442,8 @@ class HealthResponse(BaseModel):
|
||||
gpu_type: Optional[str] = None # GPU type (CUDA, MPS, or None)
|
||||
vram_used_mb: Optional[float] = None
|
||||
backend_type: Optional[str] = None # Backend type (mlx or pytorch)
|
||||
backend_variant: Optional[str] = None # Binary variant (cpu or cuda)
|
||||
backend_variant: Optional[str] = None # Binary variant (cpu, cuda, or rocm)
|
||||
supports_rocm: bool = False # AMD GPU on Windows — the ROCm backend is applicable
|
||||
gpu_compatibility_warning: Optional[str] = None # Warning if GPU arch unsupported
|
||||
|
||||
|
||||
|
||||
@@ -0,0 +1,85 @@
|
||||
"""
|
||||
Runtime hook: repair rocm_sdk.find_libraries under PyInstaller.
|
||||
|
||||
rocm_sdk 7.2.x ships a find_libraries() with a latent bug: when the
|
||||
backend package (_rocm_sdk_core / _rocm_sdk_libraries_{target}) cannot
|
||||
be imported, the except clause records the miss but falls through to
|
||||
`py_root = Path(py_module.__file__).parent`, where py_module was never
|
||||
assigned. This surfaces as UnboundLocalError instead of the intended
|
||||
ModuleNotFoundError, masking the real cause.
|
||||
|
||||
Frozen apps trip this because rocm_sdk imports the backend packages
|
||||
dynamically via importlib, which PyInstaller's static analyzer cannot
|
||||
see. We re-collect those packages in build_binary.py; this hook is
|
||||
defense-in-depth: it replaces find_libraries with a corrected version
|
||||
so any future missing-package case surfaces a readable error.
|
||||
"""
|
||||
|
||||
|
||||
def _patch_rocm_sdk():
|
||||
try:
|
||||
import rocm_sdk
|
||||
from rocm_sdk import _dist_info
|
||||
except ModuleNotFoundError as e:
|
||||
if e.name not in {"rocm_sdk", "rocm_sdk._dist_info"}:
|
||||
raise
|
||||
return
|
||||
|
||||
import importlib
|
||||
import platform
|
||||
from pathlib import Path
|
||||
|
||||
def find_libraries(*shortnames):
|
||||
paths = []
|
||||
missing_extras = set()
|
||||
is_windows = platform.system() == "Windows"
|
||||
for shortname in shortnames:
|
||||
try:
|
||||
lib_entry = _dist_info.ALL_LIBRARIES[shortname]
|
||||
except KeyError:
|
||||
raise ModuleNotFoundError(f"Unknown rocm library '{shortname}'") from None
|
||||
|
||||
if is_windows and not lib_entry.dll_pattern:
|
||||
continue
|
||||
|
||||
package = lib_entry.package
|
||||
target_family = None
|
||||
if package.is_target_specific:
|
||||
target_family = _dist_info.determine_target_family()
|
||||
py_package_name = package.get_py_package_name(target_family)
|
||||
try:
|
||||
py_module = importlib.import_module(py_package_name)
|
||||
except ModuleNotFoundError as e:
|
||||
if e.name != py_package_name:
|
||||
raise
|
||||
missing_extras.add(package.logical_name)
|
||||
continue
|
||||
|
||||
py_root = Path(py_module.__file__).parent
|
||||
if is_windows:
|
||||
relpath = py_root / lib_entry.windows_relpath
|
||||
entry_pattern = lib_entry.dll_pattern
|
||||
else:
|
||||
relpath = py_root / lib_entry.posix_relpath
|
||||
entry_pattern = lib_entry.so_pattern
|
||||
matching_paths = sorted(relpath.glob(entry_pattern))
|
||||
if len(matching_paths) == 0:
|
||||
raise FileNotFoundError(
|
||||
f"Could not find rocm library '{shortname}' at path "
|
||||
f"'{relpath},' no match for pattern '{entry_pattern}'"
|
||||
)
|
||||
paths.append(matching_paths[0])
|
||||
|
||||
if missing_extras:
|
||||
raise ModuleNotFoundError(
|
||||
f"Missing required rocm backend packages: "
|
||||
f"{', '.join(sorted(missing_extras))}. The frozen build did "
|
||||
f"not bundle _rocm_sdk_core / _rocm_sdk_libraries_<target>. "
|
||||
f"Check build_binary.py --collect-all flags."
|
||||
)
|
||||
return paths
|
||||
|
||||
rocm_sdk.find_libraries = find_libraries
|
||||
|
||||
|
||||
_patch_rocm_sdk()
|
||||
@@ -0,0 +1,4 @@
|
||||
--extra-index-url https://repo.radeon.com/rocm/windows/rocm-rel-7.2.1/
|
||||
torch==2.9.1+rocm7.2.1
|
||||
torchaudio==2.9.1+rocm7.2.1
|
||||
torchvision==0.24.1+rocm7.2.1
|
||||
@@ -20,6 +20,7 @@ def register_routers(app: FastAPI) -> None:
|
||||
from .settings import router as settings_router
|
||||
from .tasks import router as tasks_router
|
||||
from .cuda import router as cuda_router
|
||||
from .rocm import router as rocm_router
|
||||
from .speak import router as speak_router
|
||||
from .mcp_bindings import router as mcp_bindings_router
|
||||
from .events import router as events_router
|
||||
@@ -39,6 +40,7 @@ def register_routers(app: FastAPI) -> None:
|
||||
app.include_router(settings_router)
|
||||
app.include_router(tasks_router)
|
||||
app.include_router(cuda_router)
|
||||
app.include_router(rocm_router)
|
||||
app.include_router(speak_router)
|
||||
app.include_router(mcp_bindings_router)
|
||||
app.include_router(events_router)
|
||||
|
||||
@@ -13,7 +13,7 @@ from sqlalchemy.orm import Session
|
||||
from .. import config, models
|
||||
from ..services import tts
|
||||
from ..database import get_db
|
||||
from ..utils.platform_detect import get_backend_type
|
||||
from ..utils.platform_detect import get_backend_type, is_amd_gpu_windows
|
||||
|
||||
router = APIRouter()
|
||||
|
||||
@@ -103,7 +103,10 @@ async def health():
|
||||
|
||||
gpu_type = None
|
||||
if has_cuda:
|
||||
gpu_type = f"CUDA ({torch.cuda.get_device_name(0)})"
|
||||
if hasattr(torch.version, "hip") and torch.version.hip:
|
||||
gpu_type = f"ROCm ({torch.cuda.get_device_name(0)})"
|
||||
else:
|
||||
gpu_type = f"CUDA ({torch.cuda.get_device_name(0)})"
|
||||
elif has_mps:
|
||||
gpu_type = "MPS (Apple Silicon)"
|
||||
elif backend_type == "mlx":
|
||||
@@ -164,6 +167,15 @@ async def health():
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
default_variant = "cpu"
|
||||
if has_cuda:
|
||||
if hasattr(torch.version, "hip") and torch.version.hip:
|
||||
default_variant = "rocm"
|
||||
else:
|
||||
default_variant = "cuda"
|
||||
elif has_xpu:
|
||||
default_variant = "xpu"
|
||||
|
||||
return models.HealthResponse(
|
||||
status="healthy",
|
||||
model_loaded=model_loaded,
|
||||
@@ -173,10 +185,8 @@ async def health():
|
||||
gpu_type=gpu_type,
|
||||
vram_used_mb=vram_used,
|
||||
backend_type=backend_type,
|
||||
backend_variant=os.environ.get(
|
||||
"VOICEBOX_BACKEND_VARIANT",
|
||||
"cuda" if torch.cuda.is_available() else ("xpu" if has_xpu else "cpu"),
|
||||
),
|
||||
backend_variant=os.environ.get("VOICEBOX_BACKEND_VARIANT", default_variant),
|
||||
supports_rocm=is_amd_gpu_windows(),
|
||||
gpu_compatibility_warning=gpu_compat_warning,
|
||||
)
|
||||
|
||||
|
||||
@@ -0,0 +1,79 @@
|
||||
"""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",
|
||||
},
|
||||
)
|
||||
+13
-10
@@ -7,6 +7,7 @@ absolute imports instead of relative imports.
|
||||
|
||||
import sys
|
||||
import os
|
||||
import re
|
||||
|
||||
# On Windows with --noconsole (PyInstaller), sys.stdout/stderr are None.
|
||||
# They can also be broken file objects in some edge cases.
|
||||
@@ -47,6 +48,17 @@ if "--version" in sys.argv:
|
||||
print(f"voicebox-server {__version__}")
|
||||
sys.exit(0)
|
||||
|
||||
# Detect backend variant from binary name BEFORE importing backend modules
|
||||
# so that env-var guards in app.py (e.g. HSA_OVERRIDE_GFX_VERSION) fire at import time.
|
||||
_binary_name = os.path.basename(sys.executable).lower()
|
||||
if re.search(r"voicebox-server-rocm(\.exe)?$", _binary_name):
|
||||
os.environ["VOICEBOX_BACKEND_VARIANT"] = "rocm"
|
||||
elif re.search(r"voicebox-server-cuda(\.exe)?$", _binary_name):
|
||||
os.environ["VOICEBOX_BACKEND_VARIANT"] = "cuda"
|
||||
else:
|
||||
os.environ.setdefault("VOICEBOX_BACKEND_VARIANT", "cpu")
|
||||
|
||||
|
||||
import logging
|
||||
|
||||
# Set up logging FIRST, before any imports that might fail
|
||||
@@ -260,16 +272,7 @@ if __name__ == "__main__":
|
||||
if args.parent_pid is not None and args.parent_pid <= 0:
|
||||
parser.error("--parent-pid must be a positive integer")
|
||||
|
||||
# Detect backend variant from binary name
|
||||
# voicebox-server-cuda → sets VOICEBOX_BACKEND_VARIANT=cuda
|
||||
import os
|
||||
binary_name = os.path.basename(sys.executable).lower()
|
||||
if "cuda" in binary_name:
|
||||
os.environ["VOICEBOX_BACKEND_VARIANT"] = "cuda"
|
||||
logger.info("Backend variant: CUDA")
|
||||
else:
|
||||
os.environ["VOICEBOX_BACKEND_VARIANT"] = "cpu"
|
||||
logger.info("Backend variant: CPU")
|
||||
logger.info(f"Backend variant: {os.environ.get('VOICEBOX_BACKEND_VARIANT', 'cpu').upper()}")
|
||||
|
||||
# Register parent watchdog to start after server is fully ready
|
||||
if args.parent_pid is not None:
|
||||
|
||||
@@ -0,0 +1,467 @@
|
||||
"""
|
||||
ROCm backend download, assembly, and verification.
|
||||
|
||||
Downloads two archives from GitHub Releases:
|
||||
1. Server core (voicebox-server-rocm.tar.gz) — the exe + non-AMD deps,
|
||||
versioned with the app.
|
||||
2. ROCm libs (rocm-libs-{version}.tar.gz) — AMD runtime libraries,
|
||||
versioned independently (only redownloaded on ROCm toolkit bump).
|
||||
|
||||
Both archives are extracted into {data_dir}/backends/rocm/ which forms the
|
||||
complete PyInstaller --onedir directory structure that torch expects.
|
||||
"""
|
||||
|
||||
import asyncio
|
||||
import hashlib
|
||||
import json
|
||||
import logging
|
||||
import os
|
||||
import shutil
|
||||
import sys
|
||||
import tarfile
|
||||
from pathlib import Path
|
||||
from typing import Optional
|
||||
|
||||
from ..config import get_data_dir
|
||||
from ..utils.progress import get_progress_manager
|
||||
from .. import __version__
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
GITHUB_RELEASES_URL = "https://github.com/jamiepine/voicebox/releases/download"
|
||||
|
||||
PROGRESS_KEY = "rocm-backend"
|
||||
|
||||
# The current expected ROCm libs version. Bump this when we change the
|
||||
# ROCm toolkit version or torch's ROCm dependency changes (e.g. rocm7.2 -> rocm7.4).
|
||||
ROCM_LIBS_VERSION = "rocm7.2-v1"
|
||||
|
||||
# Prevents concurrent download_rocm_binary() calls from racing on the same
|
||||
# temp file. The auto-update background task and the manual HTTP endpoint
|
||||
# can both invoke download_rocm_binary(); without this lock the progress-
|
||||
# manager status check is a TOCTOU race.
|
||||
_download_lock = asyncio.Lock()
|
||||
|
||||
|
||||
def get_backends_dir() -> Path:
|
||||
"""Directory where downloaded backend binaries are stored."""
|
||||
d = get_data_dir() / "backends"
|
||||
d.mkdir(parents=True, exist_ok=True)
|
||||
return d
|
||||
|
||||
|
||||
def get_rocm_dir() -> Path:
|
||||
"""Directory where the ROCm backend (onedir) is extracted."""
|
||||
d = get_backends_dir() / "rocm"
|
||||
d.mkdir(parents=True, exist_ok=True)
|
||||
return d
|
||||
|
||||
|
||||
def get_rocm_exe_name() -> str:
|
||||
"""Platform-specific ROCm executable filename."""
|
||||
if sys.platform == "win32":
|
||||
return "voicebox-server-rocm.exe"
|
||||
return "voicebox-server-rocm"
|
||||
|
||||
|
||||
def get_rocm_binary_path() -> Optional[Path]:
|
||||
"""Return path to the ROCm executable if it exists inside the onedir."""
|
||||
p = get_rocm_dir() / get_rocm_exe_name()
|
||||
if p.exists():
|
||||
return p
|
||||
return None
|
||||
|
||||
|
||||
def get_rocm_libs_manifest_path() -> Path:
|
||||
"""Path to the rocm-libs.json manifest inside the ROCm dir."""
|
||||
return get_rocm_dir() / "rocm-libs.json"
|
||||
|
||||
|
||||
def get_installed_rocm_libs_version() -> Optional[str]:
|
||||
"""Read the installed ROCm libs version from rocm-libs.json, or None."""
|
||||
manifest_path = get_rocm_libs_manifest_path()
|
||||
if not manifest_path.exists():
|
||||
return None
|
||||
try:
|
||||
data = json.loads(manifest_path.read_text())
|
||||
return data.get("version")
|
||||
except Exception as e:
|
||||
logger.warning(f"Could not read rocm-libs.json: {e}")
|
||||
return None
|
||||
|
||||
|
||||
def is_rocm_active() -> bool:
|
||||
"""Check if the current process is the ROCm binary.
|
||||
|
||||
The ROCm binary sets this env var on startup (see server.py).
|
||||
"""
|
||||
return os.environ.get("VOICEBOX_BACKEND_VARIANT") == "rocm"
|
||||
|
||||
|
||||
def get_rocm_status() -> dict:
|
||||
"""Get current ROCm backend status for the API."""
|
||||
progress_manager = get_progress_manager()
|
||||
rocm_path = get_rocm_binary_path()
|
||||
progress = progress_manager.get_progress(PROGRESS_KEY)
|
||||
rocm_libs_version = get_installed_rocm_libs_version()
|
||||
|
||||
return {
|
||||
"available": rocm_path is not None,
|
||||
"active": is_rocm_active(),
|
||||
"binary_path": str(rocm_path) if rocm_path else None,
|
||||
"rocm_libs_version": rocm_libs_version,
|
||||
"downloading": progress is not None and progress.get("status") == "downloading",
|
||||
"download_progress": progress,
|
||||
}
|
||||
|
||||
|
||||
def _needs_server_download(version: Optional[str] = None) -> bool:
|
||||
"""Check if the server core archive needs to be (re)downloaded."""
|
||||
rocm_path = get_rocm_binary_path()
|
||||
if not rocm_path:
|
||||
return True
|
||||
# Check if the binary version matches the expected app version
|
||||
installed = get_rocm_binary_version()
|
||||
expected = version or __version__
|
||||
if expected.startswith("v"):
|
||||
expected = expected[1:]
|
||||
return installed != expected
|
||||
|
||||
|
||||
def _needs_rocm_libs_download() -> bool:
|
||||
"""Check if the ROCm libs archive needs to be (re)downloaded."""
|
||||
installed = get_installed_rocm_libs_version()
|
||||
if installed is None:
|
||||
return True
|
||||
return installed != ROCM_LIBS_VERSION
|
||||
|
||||
|
||||
async def _download_and_extract_archive(
|
||||
client,
|
||||
url: str,
|
||||
sha256_url: Optional[str],
|
||||
dest_dir: Path,
|
||||
label: str,
|
||||
progress_offset: int,
|
||||
total_size: int,
|
||||
):
|
||||
"""Download a .tar.gz archive and extract it into dest_dir.
|
||||
|
||||
Args:
|
||||
client: httpx.AsyncClient
|
||||
url: URL of the .tar.gz archive
|
||||
sha256_url: URL of the .sha256 checksum file (optional)
|
||||
dest_dir: Directory to extract into
|
||||
label: Human-readable label for progress updates
|
||||
progress_offset: Byte offset for progress reporting (when downloading
|
||||
multiple archives sequentially)
|
||||
total_size: Total bytes across all downloads (for progress bar)
|
||||
"""
|
||||
progress = get_progress_manager()
|
||||
temp_path = dest_dir / f".download-{label.replace(' ', '-')}.tmp"
|
||||
|
||||
# Clean up leftover partial download
|
||||
if temp_path.exists():
|
||||
temp_path.unlink()
|
||||
|
||||
# Fetch expected checksum (fail-fast: never extract an unverified archive)
|
||||
expected_sha = None
|
||||
if sha256_url:
|
||||
try:
|
||||
sha_resp = await client.get(sha256_url)
|
||||
sha_resp.raise_for_status()
|
||||
expected_sha = sha_resp.text.strip().split()[0]
|
||||
logger.info(f"{label}: expected SHA-256: {expected_sha[:16]}...")
|
||||
except Exception as e:
|
||||
raise RuntimeError(f"{label}: failed to fetch checksum from {sha256_url}") from e
|
||||
|
||||
# Stream download, verify, and extract — always clean up temp file
|
||||
downloaded = 0
|
||||
try:
|
||||
async with client.stream("GET", url) as response:
|
||||
response.raise_for_status()
|
||||
with open(temp_path, "wb") as f:
|
||||
async for chunk in response.aiter_bytes(chunk_size=1024 * 1024):
|
||||
f.write(chunk)
|
||||
downloaded += len(chunk)
|
||||
progress.update_progress(
|
||||
PROGRESS_KEY,
|
||||
current=progress_offset + downloaded,
|
||||
total=total_size,
|
||||
filename=f"Downloading {label}",
|
||||
status="downloading",
|
||||
)
|
||||
|
||||
# Verify integrity
|
||||
if expected_sha:
|
||||
progress.update_progress(
|
||||
PROGRESS_KEY,
|
||||
current=progress_offset + downloaded,
|
||||
total=total_size,
|
||||
filename=f"Verifying {label}...",
|
||||
status="downloading",
|
||||
)
|
||||
sha256 = hashlib.sha256()
|
||||
with open(temp_path, "rb") as f:
|
||||
while True:
|
||||
data = f.read(1024 * 1024)
|
||||
if not data:
|
||||
break
|
||||
sha256.update(data)
|
||||
actual = sha256.hexdigest()
|
||||
if actual != expected_sha:
|
||||
raise ValueError(
|
||||
f"{label} integrity check failed: expected {expected_sha[:16]}..., got {actual[:16]}..."
|
||||
)
|
||||
logger.info(f"{label}: integrity verified")
|
||||
|
||||
# Extract (use data filter for path traversal protection on Python 3.12+)
|
||||
progress.update_progress(
|
||||
PROGRESS_KEY,
|
||||
current=progress_offset + downloaded,
|
||||
total=total_size,
|
||||
filename=f"Extracting {label}...",
|
||||
status="downloading",
|
||||
)
|
||||
with tarfile.open(temp_path, "r:gz") as tar:
|
||||
tar.extractall(path=dest_dir, filter="data")
|
||||
|
||||
logger.info(f"{label}: extracted to {dest_dir}")
|
||||
finally:
|
||||
if temp_path.exists():
|
||||
temp_path.unlink()
|
||||
return downloaded
|
||||
|
||||
|
||||
async def download_rocm_binary(version: Optional[str] = None):
|
||||
"""Download the ROCm backend (server core + ROCm libs if needed).
|
||||
|
||||
Downloads both archives from GitHub Releases, extracts them into
|
||||
{data_dir}/backends/rocm/, and writes the rocm-libs.json manifest.
|
||||
|
||||
Only downloads what's needed:
|
||||
- Server core: always redownloaded (versioned with app)
|
||||
- ROCm libs: only if missing or version mismatch
|
||||
|
||||
Args:
|
||||
version: Version tag (e.g. "v0.3.0"). Defaults to current app version.
|
||||
"""
|
||||
if _download_lock.locked():
|
||||
logger.info("ROCm download already in progress, skipping duplicate request")
|
||||
return
|
||||
async with _download_lock:
|
||||
await _download_rocm_binary_locked(version)
|
||||
|
||||
|
||||
async def _download_rocm_binary_locked(version: Optional[str] = None):
|
||||
"""Inner implementation of download_rocm_binary, called under _download_lock."""
|
||||
import httpx
|
||||
|
||||
if version is None:
|
||||
version = f"v{__version__}"
|
||||
|
||||
progress = get_progress_manager()
|
||||
rocm_dir = get_rocm_dir()
|
||||
|
||||
need_server = _needs_server_download(version)
|
||||
need_libs = _needs_rocm_libs_download()
|
||||
|
||||
if not need_server and not need_libs:
|
||||
logger.info("ROCm backend is up to date, nothing to download")
|
||||
return
|
||||
|
||||
logger.info(
|
||||
f"Starting ROCm backend download for {version} "
|
||||
f"(server={'yes' if need_server else 'cached'}, "
|
||||
f"libs={'yes' if need_libs else 'cached'})"
|
||||
)
|
||||
progress.update_progress(
|
||||
PROGRESS_KEY,
|
||||
current=0,
|
||||
total=0,
|
||||
filename="Preparing download...",
|
||||
status="downloading",
|
||||
)
|
||||
|
||||
# Server core and libs archive are both published under the app-version
|
||||
# release tag; the libs content version is encoded in the filename only.
|
||||
server_base_url = f"{GITHUB_RELEASES_URL}/{version}"
|
||||
libs_base_url = server_base_url
|
||||
server_archive = "voicebox-server-rocm.tar.gz"
|
||||
libs_archive = f"rocm-libs-{ROCM_LIBS_VERSION}.tar.gz"
|
||||
|
||||
# Always stage when any download is needed, then atomically rename over
|
||||
# rocm_dir on success. This prevents a failed mid-extraction from leaving
|
||||
# rocm_dir in a partially-installed state that still passes the
|
||||
# get_rocm_binary_path() existence check. Existing files are pre-copied
|
||||
# into staging so partial updates (e.g. libs-only or server-only) preserve
|
||||
# whatever isn't being re-downloaded.
|
||||
use_staging = need_server or need_libs
|
||||
staging_dir = get_backends_dir() / "rocm-staging"
|
||||
|
||||
if use_staging:
|
||||
if staging_dir.exists():
|
||||
shutil.rmtree(staging_dir)
|
||||
staging_dir.mkdir(parents=True, exist_ok=True)
|
||||
# Preserve existing files (server or libs) that don't need re-downloading.
|
||||
# Extracted archives will overwrite only what we actually download.
|
||||
if rocm_dir.exists():
|
||||
shutil.copytree(rocm_dir, staging_dir, dirs_exist_ok=True)
|
||||
extract_dir = staging_dir
|
||||
else:
|
||||
extract_dir = rocm_dir
|
||||
|
||||
try:
|
||||
async with httpx.AsyncClient(follow_redirects=True, timeout=30.0) as client:
|
||||
# Estimate total download size
|
||||
total_size = 0
|
||||
if need_server:
|
||||
try:
|
||||
head = await client.head(f"{server_base_url}/{server_archive}")
|
||||
total_size += int(head.headers.get("content-length", 0))
|
||||
except Exception:
|
||||
pass
|
||||
if need_libs:
|
||||
try:
|
||||
head = await client.head(f"{libs_base_url}/{libs_archive}")
|
||||
total_size += int(head.headers.get("content-length", 0))
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
logger.info(f"Total download size: {total_size / 1024 / 1024:.1f} MB")
|
||||
|
||||
offset = 0
|
||||
|
||||
# Download server core
|
||||
if need_server:
|
||||
server_downloaded = await _download_and_extract_archive(
|
||||
client,
|
||||
url=f"{server_base_url}/{server_archive}",
|
||||
sha256_url=f"{server_base_url}/{server_archive}.sha256",
|
||||
dest_dir=extract_dir,
|
||||
label="ROCm server",
|
||||
progress_offset=offset,
|
||||
total_size=total_size,
|
||||
)
|
||||
offset += server_downloaded
|
||||
|
||||
# Make executable on Unix
|
||||
exe_path = extract_dir / get_rocm_exe_name()
|
||||
if sys.platform != "win32" and exe_path.exists():
|
||||
exe_path.chmod(0o755)
|
||||
|
||||
# Download ROCm libs
|
||||
if need_libs:
|
||||
await _download_and_extract_archive(
|
||||
client,
|
||||
url=f"{libs_base_url}/{libs_archive}",
|
||||
sha256_url=f"{libs_base_url}/{libs_archive}.sha256",
|
||||
dest_dir=extract_dir,
|
||||
label="ROCm libraries",
|
||||
progress_offset=offset,
|
||||
total_size=total_size,
|
||||
)
|
||||
|
||||
# Write local rocm-libs.json manifest
|
||||
manifest = {"version": ROCM_LIBS_VERSION}
|
||||
(extract_dir / "rocm-libs.json").write_text(json.dumps(manifest, indent=2) + "\n")
|
||||
|
||||
# Atomic swap: replace rocm_dir with the fully-extracted staging dir
|
||||
if use_staging:
|
||||
backup_dir = get_backends_dir() / "rocm-backup"
|
||||
if backup_dir.exists():
|
||||
shutil.rmtree(backup_dir)
|
||||
if rocm_dir.exists():
|
||||
rocm_dir.rename(backup_dir)
|
||||
try:
|
||||
staging_dir.rename(rocm_dir)
|
||||
except Exception:
|
||||
if backup_dir.exists() and not rocm_dir.exists():
|
||||
backup_dir.rename(rocm_dir)
|
||||
raise
|
||||
else:
|
||||
if backup_dir.exists():
|
||||
shutil.rmtree(backup_dir)
|
||||
|
||||
logger.info(f"ROCm backend ready at {rocm_dir}")
|
||||
progress.mark_complete(PROGRESS_KEY)
|
||||
|
||||
except Exception as e:
|
||||
if use_staging and staging_dir.exists():
|
||||
shutil.rmtree(staging_dir)
|
||||
logger.error(f"ROCm backend download failed: {e}")
|
||||
progress.mark_error(PROGRESS_KEY, str(e))
|
||||
raise
|
||||
|
||||
|
||||
def get_rocm_binary_version() -> Optional[str]:
|
||||
"""Get the version of the installed ROCm binary, or None if not installed."""
|
||||
import subprocess
|
||||
|
||||
rocm_path = get_rocm_binary_path()
|
||||
if not rocm_path:
|
||||
return None
|
||||
try:
|
||||
result = subprocess.run(
|
||||
[str(rocm_path), "--version"],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=30,
|
||||
cwd=str(rocm_path.parent), # Run from the onedir directory
|
||||
)
|
||||
# Output format: "voicebox-server 0.3.0"
|
||||
for line in result.stdout.strip().splitlines():
|
||||
if "voicebox-server" in line:
|
||||
return line.split()[-1]
|
||||
except Exception as e:
|
||||
logger.warning(f"Could not get ROCm binary version: {e}")
|
||||
return None
|
||||
|
||||
|
||||
async def check_and_update_rocm_binary():
|
||||
"""Check if the ROCm binary is outdated and auto-download if so.
|
||||
|
||||
Called on server startup. Checks both server version and ROCm libs
|
||||
version. Downloads only what's needed.
|
||||
"""
|
||||
rocm_path = get_rocm_binary_path()
|
||||
if not rocm_path:
|
||||
return # No ROCm binary installed, nothing to update
|
||||
|
||||
if is_rocm_active():
|
||||
logger.info("ROCm backend is active; skipping auto-update to avoid replacing the running backend")
|
||||
return
|
||||
|
||||
need_server = _needs_server_download()
|
||||
need_libs = _needs_rocm_libs_download()
|
||||
|
||||
if not need_server and not need_libs:
|
||||
logger.info(f"ROCm binary is up to date (server=v{__version__}, libs={get_installed_rocm_libs_version()})")
|
||||
return
|
||||
|
||||
reasons = []
|
||||
if need_server:
|
||||
rocm_version = get_rocm_binary_version()
|
||||
reasons.append(f"server v{rocm_version} != v{__version__}")
|
||||
if need_libs:
|
||||
installed_libs = get_installed_rocm_libs_version()
|
||||
reasons.append(f"libs {installed_libs} != {ROCM_LIBS_VERSION}")
|
||||
|
||||
logger.info(f"ROCm backend needs update ({', '.join(reasons)}). Auto-downloading...")
|
||||
|
||||
try:
|
||||
await download_rocm_binary()
|
||||
except Exception as e:
|
||||
logger.error(f"Auto-update of ROCm binary failed: {e}")
|
||||
|
||||
|
||||
async def delete_rocm_binary() -> bool:
|
||||
"""Delete the downloaded ROCm backend directory. Returns True if deleted."""
|
||||
import shutil
|
||||
|
||||
rocm_dir = get_rocm_dir()
|
||||
if rocm_dir.exists() and any(rocm_dir.iterdir()):
|
||||
shutil.rmtree(rocm_dir)
|
||||
logger.info(f"Deleted ROCm backend directory: {rocm_dir}")
|
||||
return True
|
||||
return False
|
||||
@@ -0,0 +1,96 @@
|
||||
"""
|
||||
Phase 2.1 Test: AMD GPU detection on Windows.
|
||||
|
||||
Validates is_amd_gpu_windows() via mocked WMI and torch queries.
|
||||
|
||||
Usage:
|
||||
python -m pytest backend/tests/test_amd_gpu_detect.py -v
|
||||
"""
|
||||
|
||||
from unittest.mock import MagicMock, patch
|
||||
|
||||
import pytest
|
||||
|
||||
from backend.utils.platform_detect import is_amd_gpu_windows
|
||||
|
||||
|
||||
class TestAmdGpuWindows:
|
||||
"""Unit tests for is_amd_gpu_windows with mocks."""
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def _clear_detection_cache(self):
|
||||
# is_amd_gpu_windows is memoized; reset between cases so each mock takes effect.
|
||||
is_amd_gpu_windows.cache_clear()
|
||||
yield
|
||||
is_amd_gpu_windows.cache_clear()
|
||||
|
||||
@patch("backend.utils.platform_detect.platform.system", return_value="Linux")
|
||||
def test_returns_false_on_linux(self, _mock_system):
|
||||
"""Non-Windows platforms should always return False."""
|
||||
assert is_amd_gpu_windows() is False
|
||||
|
||||
@patch("backend.utils.platform_detect.platform.system", return_value="Windows")
|
||||
@patch(
|
||||
"backend.utils.platform_detect.subprocess.run",
|
||||
return_value=MagicMock(stdout="1\n", returncode=0),
|
||||
)
|
||||
def test_detects_amd_via_wmi(self, _mock_run, _mock_system):
|
||||
"""WMI reporting an AMD adapter should return True."""
|
||||
assert is_amd_gpu_windows() is True
|
||||
|
||||
@patch("backend.utils.platform_detect.platform.system", return_value="Windows")
|
||||
@patch(
|
||||
"backend.utils.platform_detect.subprocess.run",
|
||||
return_value=MagicMock(stdout="0\n", returncode=0),
|
||||
)
|
||||
def test_no_amd_via_wmi(self, _mock_run, _mock_system):
|
||||
"""WMI reporting zero AMD adapters should return False."""
|
||||
assert is_amd_gpu_windows() is False
|
||||
|
||||
@patch("backend.utils.platform_detect.platform.system", return_value="Windows")
|
||||
@patch(
|
||||
"backend.utils.platform_detect.subprocess.run",
|
||||
side_effect=Exception("WMI not available"),
|
||||
)
|
||||
@patch("torch.cuda.is_available", return_value=True)
|
||||
@patch(
|
||||
"torch.cuda.get_device_name",
|
||||
return_value="AMD Radeon RX 7800 XT",
|
||||
)
|
||||
def test_fallback_to_torch_radeon(self, _mock_name, _mock_avail, _mock_run, _mock_system):
|
||||
"""When WMI fails, torch.cuda.get_device_name('Radeon') should return True."""
|
||||
assert is_amd_gpu_windows() is True
|
||||
|
||||
@patch("backend.utils.platform_detect.platform.system", return_value="Windows")
|
||||
@patch(
|
||||
"backend.utils.platform_detect.subprocess.run",
|
||||
side_effect=Exception("WMI not available"),
|
||||
)
|
||||
@patch("torch.cuda.is_available", return_value=True)
|
||||
@patch(
|
||||
"torch.cuda.get_device_name",
|
||||
return_value="NVIDIA GeForce RTX 4090",
|
||||
)
|
||||
def test_fallback_to_torch_nvidia(self, _mock_name, _mock_avail, _mock_run, _mock_system):
|
||||
"""When WMI fails, torch.cuda.get_device_name('NVIDIA') should return False."""
|
||||
assert is_amd_gpu_windows() is False
|
||||
|
||||
@patch("backend.utils.platform_detect.platform.system", return_value="Windows")
|
||||
@patch(
|
||||
"backend.utils.platform_detect.subprocess.run",
|
||||
side_effect=Exception("WMI not available"),
|
||||
)
|
||||
@patch("torch.cuda.is_available", return_value=False)
|
||||
def test_no_torch_cuda(self, _mock_avail, _mock_run, _mock_system):
|
||||
"""When WMI fails and torch.cuda is unavailable, should return False."""
|
||||
assert is_amd_gpu_windows() is False
|
||||
|
||||
@patch("backend.utils.platform_detect.platform.system", return_value="Windows")
|
||||
@patch(
|
||||
"backend.utils.platform_detect.subprocess.run",
|
||||
side_effect=Exception("WMI not available"),
|
||||
)
|
||||
def test_torch_not_installed(self, _mock_run, _mock_system):
|
||||
"""When torch is not installed, should return False without crashing."""
|
||||
with patch.dict("sys.modules", {"torch": None}):
|
||||
assert is_amd_gpu_windows() is False
|
||||
@@ -0,0 +1,121 @@
|
||||
"""
|
||||
Tests for scripts/package_rocm.py — the ROCm onedir → server + libs splitter.
|
||||
|
||||
The classifier can't be validated against a real AMD build on CI hardware, so
|
||||
these tests pin the file-classification rules against a synthetic onedir layout
|
||||
that mirrors the PyInstaller --rocm output (torch/lib HIP DLLs + bundled
|
||||
rocm_sdk runtime packages).
|
||||
|
||||
Usage:
|
||||
python -m pytest backend/tests/test_package_rocm.py -v
|
||||
"""
|
||||
|
||||
import importlib.util
|
||||
import tarfile
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
_PACKAGE_ROCM = Path(__file__).resolve().parents[2] / "scripts" / "package_rocm.py"
|
||||
_spec = importlib.util.spec_from_file_location("package_rocm", _PACKAGE_ROCM)
|
||||
package_rocm = importlib.util.module_from_spec(_spec)
|
||||
_spec.loader.exec_module(package_rocm)
|
||||
|
||||
|
||||
class TestIsRocmFile:
|
||||
"""Classification of individual files into core vs ROCm libs."""
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"rel_path",
|
||||
[
|
||||
"_internal/torch/lib/amdhip64.dll",
|
||||
"_internal/torch/lib/rocblas.dll",
|
||||
"_internal/torch/lib/hipblaslt.dll",
|
||||
"_internal/torch/lib/miopen.dll",
|
||||
"_internal/_rocm_sdk_core/amd_comgr.dll",
|
||||
"_internal/_rocm_sdk_libraries_custom/lib/rocblas/library/TensileLibrary.dat",
|
||||
"_internal/_rocm_sdk_libraries_custom/lib/miopen/db/kernels.kdb",
|
||||
# Windows path separators must be handled too.
|
||||
"_internal\\torch\\lib\\rccl.dll",
|
||||
],
|
||||
)
|
||||
def test_runtime_files_are_rocm(self, rel_path):
|
||||
assert package_rocm.is_rocm_file(rel_path) is True
|
||||
|
||||
@pytest.mark.parametrize(
|
||||
"rel_path",
|
||||
[
|
||||
"voicebox-server-rocm.exe",
|
||||
"_internal/python312.dll",
|
||||
"_internal/torch/lib/torch_cpu.dll",
|
||||
"_internal/torch/lib/c10.dll",
|
||||
# Pure-python rocm_sdk glue stays in the core, even under an SDK dir.
|
||||
"_internal/rocm_sdk/__init__.py",
|
||||
"_internal/_rocm_sdk_core/_dist_info.py",
|
||||
"_internal/torch/_inductor/codegen/something.py",
|
||||
],
|
||||
)
|
||||
def test_core_files_are_not_rocm(self, rel_path):
|
||||
assert package_rocm.is_rocm_file(rel_path) is False
|
||||
|
||||
|
||||
def _write(path: Path, content: bytes = b"x"):
|
||||
path.parent.mkdir(parents=True, exist_ok=True)
|
||||
path.write_bytes(content)
|
||||
|
||||
|
||||
class TestPackage:
|
||||
"""End-to-end split of a synthetic onedir into the two archives."""
|
||||
|
||||
def test_split_and_manifest(self, tmp_path):
|
||||
onedir = tmp_path / "voicebox-server-rocm"
|
||||
_write(onedir / "voicebox-server-rocm.exe")
|
||||
_write(onedir / "_internal" / "python312.dll")
|
||||
_write(onedir / "_internal" / "rocm_sdk" / "__init__.py")
|
||||
_write(onedir / "_internal" / "torch" / "lib" / "torch_cpu.dll")
|
||||
_write(onedir / "_internal" / "torch" / "lib" / "amdhip64.dll")
|
||||
_write(onedir / "_internal" / "_rocm_sdk_core" / "miopen.dll")
|
||||
_write(
|
||||
onedir
|
||||
/ "_internal"
|
||||
/ "_rocm_sdk_libraries_custom"
|
||||
/ "lib"
|
||||
/ "rocblas"
|
||||
/ "library"
|
||||
/ "TensileLibrary.dat"
|
||||
)
|
||||
|
||||
out = tmp_path / "release-assets"
|
||||
package_rocm.package(onedir, out, "rocm7.2-v1", ">=2.9.0,<2.10.0")
|
||||
|
||||
server = out / "voicebox-server-rocm.tar.gz"
|
||||
libs = out / "rocm-libs-rocm7.2-v1.tar.gz"
|
||||
assert server.exists()
|
||||
assert libs.exists()
|
||||
assert (out / "voicebox-server-rocm.tar.gz.sha256").exists()
|
||||
assert (out / "rocm-libs-rocm7.2-v1.tar.gz.sha256").exists()
|
||||
|
||||
with tarfile.open(libs) as tar:
|
||||
lib_names = set(tar.getnames())
|
||||
with tarfile.open(server) as tar:
|
||||
core_names = set(tar.getnames())
|
||||
|
||||
assert "_internal/torch/lib/amdhip64.dll" in lib_names
|
||||
assert "_internal/_rocm_sdk_core/miopen.dll" in lib_names
|
||||
assert (
|
||||
"_internal/_rocm_sdk_libraries_custom/lib/rocblas/library/TensileLibrary.dat"
|
||||
in lib_names
|
||||
)
|
||||
assert "voicebox-server-rocm.exe" in core_names
|
||||
assert "_internal/torch/lib/torch_cpu.dll" in core_names
|
||||
assert "_internal/rocm_sdk/__init__.py" in core_names
|
||||
# Archives must be disjoint.
|
||||
assert lib_names.isdisjoint(core_names)
|
||||
|
||||
def test_empty_rocm_set_exits(self, tmp_path):
|
||||
onedir = tmp_path / "voicebox-server-rocm"
|
||||
_write(onedir / "voicebox-server-rocm.exe")
|
||||
_write(onedir / "_internal" / "torch" / "lib" / "torch_cpu.dll")
|
||||
|
||||
with pytest.raises(SystemExit):
|
||||
package_rocm.package(onedir, tmp_path / "out", "rocm7.2-v1", ">=2.9.0,<2.10.0")
|
||||
@@ -0,0 +1,68 @@
|
||||
"""
|
||||
Phase 2.2 Test: Backend ROCm compatibility.
|
||||
|
||||
Validates that check_cuda_compatibility() and other backend utilities
|
||||
behave correctly on ROCm/AMD hardware.
|
||||
|
||||
Usage:
|
||||
python -m pytest backend/tests/test_rocm_backends.py -v
|
||||
"""
|
||||
|
||||
from unittest.mock import patch
|
||||
|
||||
import pytest
|
||||
|
||||
|
||||
class TestCheckCudaCompatibility:
|
||||
"""Unit tests for check_cuda_compatibility with ROCm awareness."""
|
||||
|
||||
def test_no_gpu_returns_compatible(self):
|
||||
from backend.backends.base import check_cuda_compatibility
|
||||
|
||||
with patch("torch.cuda.is_available", return_value=False):
|
||||
compatible, warning = check_cuda_compatibility()
|
||||
assert compatible is True
|
||||
assert warning is None
|
||||
|
||||
def test_rocm_skips_compute_check(self):
|
||||
"""On ROCm, the NVIDIA compute-capability check should be skipped."""
|
||||
from backend.backends.base import check_cuda_compatibility
|
||||
|
||||
with patch("torch.cuda.is_available", return_value=True):
|
||||
with patch("torch.version.hip", "6.2.41133"):
|
||||
compatible, warning = check_cuda_compatibility()
|
||||
assert compatible is True
|
||||
assert warning is None
|
||||
|
||||
def test_cuda_compatible_arch(self):
|
||||
from backend.backends.base import check_cuda_compatibility
|
||||
|
||||
with patch("torch.cuda.is_available", return_value=True):
|
||||
with patch("torch.version.hip", None):
|
||||
with patch("torch.cuda.get_device_capability", return_value=(8, 6)):
|
||||
with patch("torch.cuda.get_device_name", return_value="NVIDIA GeForce RTX 3060"):
|
||||
with patch.object(
|
||||
__import__("torch").cuda, "_get_arch_list",
|
||||
return_value=["sm_80", "sm_86", "sm_89"],
|
||||
create=True,
|
||||
):
|
||||
compatible, warning = check_cuda_compatibility()
|
||||
assert compatible is True
|
||||
assert warning is None
|
||||
|
||||
def test_cuda_incompatible_arch(self):
|
||||
from backend.backends.base import check_cuda_compatibility
|
||||
|
||||
with patch("torch.cuda.is_available", return_value=True):
|
||||
with patch("torch.version.hip", None):
|
||||
with patch("torch.cuda.get_device_capability", return_value=(9, 0)):
|
||||
with patch("torch.cuda.get_device_name", return_value="NVIDIA GeForce RTX 4090"):
|
||||
with patch.object(
|
||||
__import__("torch").cuda, "_get_arch_list",
|
||||
return_value=["sm_80", "sm_86"],
|
||||
create=True,
|
||||
):
|
||||
compatible, warning = check_cuda_compatibility()
|
||||
assert compatible is False
|
||||
assert warning is not None
|
||||
assert "not supported" in warning
|
||||
@@ -0,0 +1,129 @@
|
||||
"""
|
||||
Phase 1.2 Test: ROCm build script configuration.
|
||||
|
||||
Validates that build_binary.py --rocm generates the correct PyInstaller
|
||||
arguments and optionally performs a true E2E build.
|
||||
|
||||
Usage:
|
||||
python -m pytest backend/tests/test_rocm_build.py -v
|
||||
python -m pytest backend/tests/test_rocm_build.py -v -m "slow" # include E2E
|
||||
"""
|
||||
|
||||
import subprocess
|
||||
import sys
|
||||
from pathlib import Path
|
||||
from unittest.mock import patch
|
||||
|
||||
import pytest
|
||||
|
||||
from build_binary import build_server
|
||||
|
||||
|
||||
class TestRocmBuildArgs:
|
||||
"""Validate PyInstaller arguments for ROCm builds."""
|
||||
|
||||
@pytest.fixture
|
||||
def captured_args(self):
|
||||
"""Run build_server(rocm=True) with mocked PyInstaller and return args."""
|
||||
with (
|
||||
patch("build_binary.PyInstaller.__main__.run") as mock_run,
|
||||
patch("build_binary.platform.system", return_value="Linux"),
|
||||
patch("build_binary.os.chdir"),
|
||||
):
|
||||
build_server(rocm=True)
|
||||
return mock_run.call_args[0][0]
|
||||
|
||||
def test_binary_name(self, captured_args):
|
||||
idx = captured_args.index("--name")
|
||||
assert captured_args[idx + 1] == "voicebox-server-rocm"
|
||||
|
||||
def test_pack_mode_is_onedir(self, captured_args):
|
||||
assert "--onedir" in captured_args
|
||||
assert "--onefile" not in captured_args
|
||||
|
||||
def test_hidden_imports_cuda(self, captured_args):
|
||||
"""ROCm builds must include torch.cuda hidden imports."""
|
||||
assert "torch.cuda" in captured_args
|
||||
|
||||
def test_no_cudnn_hidden_import_for_rocm(self, captured_args):
|
||||
"""ROCm builds must NOT include NVIDIA-specific cudnn hidden imports."""
|
||||
assert "torch.backends.cudnn" not in captured_args
|
||||
|
||||
def test_nvidia_excludes_present(self, captured_args):
|
||||
"""ROCm builds must exclude nvidia packages to avoid bundling ~3GB of bloat."""
|
||||
excludes = []
|
||||
for i, arg in enumerate(captured_args):
|
||||
if arg == "--exclude-module":
|
||||
excludes.append(captured_args[i + 1])
|
||||
assert "nvidia" in excludes
|
||||
assert "nvidia.cudnn" in excludes
|
||||
|
||||
|
||||
class TestRocmBuildCli:
|
||||
"""Validate CLI argument parsing for --rocm."""
|
||||
|
||||
def test_rocm_flag_parses(self):
|
||||
build_script = Path(__file__).parent.parent / "build_binary.py"
|
||||
result = subprocess.run(
|
||||
[sys.executable, str(build_script), "--rocm", "--help"],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
)
|
||||
assert result.returncode == 0
|
||||
assert "--rocm" in result.stdout
|
||||
|
||||
def test_cannot_combine_cuda_and_rocm(self):
|
||||
"""Building with both CUDA and ROCm should raise ValueError."""
|
||||
with pytest.raises(ValueError, match="Cannot build with both CUDA and ROCm"):
|
||||
build_server(cuda=True, rocm=True)
|
||||
|
||||
|
||||
@pytest.mark.slow()
|
||||
@pytest.mark.skipif(sys.platform != "win32", reason="ROCm build E2E only runs on Windows")
|
||||
class TestRocmBuildE2E:
|
||||
"""
|
||||
True end-to-end build test.
|
||||
Executes build_binary.py --rocm, verifies the binary exists, and runs it
|
||||
with --help to confirm it boots without import errors.
|
||||
"""
|
||||
|
||||
def test_rocm_binary_compiles_and_runs(self, tmp_path):
|
||||
backend_dir = Path(__file__).parent.parent
|
||||
build_script = backend_dir / "build_binary.py"
|
||||
dist_dir = backend_dir / "dist"
|
||||
binary_dir = dist_dir / "voicebox-server-rocm"
|
||||
binary_exe = binary_dir / "voicebox-server-rocm.exe"
|
||||
|
||||
# Clean previous dist if it exists to ensure a fresh build
|
||||
if binary_dir.exists():
|
||||
import shutil
|
||||
shutil.rmtree(binary_dir)
|
||||
|
||||
# Run the full build (this can take several minutes)
|
||||
result = subprocess.run(
|
||||
[sys.executable, str(build_script), "--rocm"],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
cwd=str(backend_dir),
|
||||
timeout=900,
|
||||
)
|
||||
|
||||
assert result.returncode == 0, (
|
||||
f"Build failed with stdout:\n{result.stdout}\nstderr:\n{result.stderr}"
|
||||
)
|
||||
assert binary_exe.exists(), (
|
||||
f"Expected binary not found at {binary_exe}"
|
||||
)
|
||||
|
||||
# Run the binary with --help to ensure it boots without import errors
|
||||
run_result = subprocess.run(
|
||||
[str(binary_exe), "--help"],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
timeout=60,
|
||||
)
|
||||
|
||||
# A frozen binary may not have argparse help, but it should not crash
|
||||
# with a ModuleNotFoundError or similar import error.
|
||||
assert "ModuleNotFoundError" not in run_result.stderr
|
||||
assert "ImportError" not in run_result.stderr
|
||||
@@ -0,0 +1,203 @@
|
||||
"""
|
||||
Tests for the ROCm backend download service.
|
||||
|
||||
Mocks httpx to verify download, extraction, and progress reporting
|
||||
without hitting the network.
|
||||
"""
|
||||
|
||||
import json
|
||||
import tarfile
|
||||
import tempfile
|
||||
from io import BytesIO
|
||||
from pathlib import Path
|
||||
from unittest.mock import AsyncMock, MagicMock, patch
|
||||
|
||||
import pytest
|
||||
|
||||
from backend.services import rocm
|
||||
from backend.utils.progress import get_progress_manager
|
||||
|
||||
|
||||
@pytest.fixture(autouse=True)
|
||||
def reset_progress_manager():
|
||||
"""Reset the global progress manager before each test."""
|
||||
import backend.utils.progress
|
||||
backend.utils.progress._progress_manager = None
|
||||
yield
|
||||
backend.utils.progress._progress_manager = None
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def mock_backends_dir(tmp_path: Path, monkeypatch):
|
||||
"""Patch get_data_dir so downloads land in a temp directory."""
|
||||
monkeypatch.setattr(rocm, "get_backends_dir", lambda: tmp_path / "backends")
|
||||
return tmp_path / "backends"
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def fake_tar_gz():
|
||||
"""Create an in-memory .tar.gz archive containing a dummy file."""
|
||||
buf = BytesIO()
|
||||
with tarfile.open(fileobj=buf, mode="w:gz") as tar:
|
||||
data = b"fake binary content"
|
||||
info = tarfile.TarInfo(name="voicebox-server-rocm.exe")
|
||||
info.size = len(data)
|
||||
tar.addfile(info, BytesIO(data))
|
||||
buf.seek(0)
|
||||
return buf.read()
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def fake_sha256():
|
||||
"""Return a dummy SHA-256 hex string."""
|
||||
return "a" * 64
|
||||
|
||||
|
||||
class FakeResponse:
|
||||
"""Minimal fake for httpx.Response."""
|
||||
|
||||
def __init__(self, content: bytes = b"", status_code: int = 200, headers: dict | None = None):
|
||||
self.content = content
|
||||
self.status_code = status_code
|
||||
self.headers = headers or {}
|
||||
|
||||
def raise_for_status(self):
|
||||
if self.status_code >= 400:
|
||||
raise Exception(f"HTTP {self.status_code}")
|
||||
|
||||
def iter_bytes(self, chunk_size: int = 1024):
|
||||
for i in range(0, len(self.content), chunk_size):
|
||||
yield self.content[i : i + chunk_size]
|
||||
|
||||
async def aiter_bytes(self, chunk_size: int = 1024):
|
||||
for i in range(0, len(self.content), chunk_size):
|
||||
yield self.content[i : i + chunk_size]
|
||||
|
||||
@property
|
||||
def text(self):
|
||||
return self.content.decode()
|
||||
|
||||
|
||||
class FakeHttpxClient:
|
||||
"""Minimal fake for httpx.AsyncClient."""
|
||||
|
||||
def __init__(self, responses: dict[str, FakeResponse]):
|
||||
self._responses = responses
|
||||
|
||||
async def __aenter__(self):
|
||||
return self
|
||||
|
||||
async def __aexit__(self, *args):
|
||||
return False
|
||||
|
||||
async def head(self, url: str):
|
||||
return self._responses.get(url, FakeResponse(status_code=404))
|
||||
|
||||
async def get(self, url: str):
|
||||
return self._responses.get(url, FakeResponse(status_code=404))
|
||||
|
||||
def stream(self, method: str, url: str):
|
||||
resp = self._responses.get(url, FakeResponse(status_code=404))
|
||||
resp.raise_for_status()
|
||||
|
||||
class _Streamer:
|
||||
async def __aenter__(self):
|
||||
return resp
|
||||
|
||||
async def __aexit__(self, *args):
|
||||
return False
|
||||
|
||||
async def aiter_bytes(self, chunk_size: int = 1024):
|
||||
for i in range(0, len(resp.content), chunk_size):
|
||||
yield resp.content[i : i + chunk_size]
|
||||
|
||||
return _Streamer()
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_get_rocm_status_not_installed(mock_backends_dir):
|
||||
status = rocm.get_rocm_status()
|
||||
assert status["available"] is False
|
||||
assert status["active"] is False
|
||||
assert status["binary_path"] is None
|
||||
assert status["downloading"] is False
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_download_rocm_binary_progress_reporting(mock_backends_dir, fake_tar_gz, fake_sha256):
|
||||
"""
|
||||
Verify that download_rocm_binary():
|
||||
1. Downloads the server archive and ROCm libs archive.
|
||||
2. Extracts them into the backends/rocm directory.
|
||||
3. Reports progress via the progress_manager.
|
||||
"""
|
||||
import hashlib
|
||||
|
||||
server_sha = hashlib.sha256(fake_tar_gz).hexdigest()
|
||||
libs_sha = hashlib.sha256(fake_tar_gz).hexdigest()
|
||||
|
||||
responses = {
|
||||
"https://github.com/jamiepine/voicebox/releases/download/v0.2.3/voicebox-server-rocm.tar.gz": FakeResponse(
|
||||
content=fake_tar_gz,
|
||||
headers={"content-length": str(len(fake_tar_gz))},
|
||||
),
|
||||
"https://github.com/jamiepine/voicebox/releases/download/v0.2.3/voicebox-server-rocm.tar.gz.sha256": FakeResponse(
|
||||
content=f"{server_sha} voicebox-server-rocm.tar.gz\n".encode(),
|
||||
),
|
||||
f"https://github.com/jamiepine/voicebox/releases/download/v0.2.3/rocm-libs-{rocm.ROCM_LIBS_VERSION}.tar.gz": FakeResponse(
|
||||
content=fake_tar_gz,
|
||||
headers={"content-length": str(len(fake_tar_gz))},
|
||||
),
|
||||
f"https://github.com/jamiepine/voicebox/releases/download/v0.2.3/rocm-libs-{rocm.ROCM_LIBS_VERSION}.tar.gz.sha256": FakeResponse(
|
||||
content=f"{libs_sha} rocm-libs.tar.gz\n".encode(),
|
||||
),
|
||||
}
|
||||
|
||||
fake_client = FakeHttpxClient(responses)
|
||||
|
||||
with patch("httpx.AsyncClient", return_value=fake_client):
|
||||
await rocm.download_rocm_binary(version="v0.2.3")
|
||||
|
||||
# Verify extraction
|
||||
rocm_dir = rocm.get_rocm_dir()
|
||||
assert (rocm_dir / "voicebox-server-rocm.exe").exists()
|
||||
|
||||
# Verify manifest written
|
||||
manifest_path = rocm.get_rocm_libs_manifest_path()
|
||||
assert manifest_path.exists()
|
||||
data = json.loads(manifest_path.read_text())
|
||||
assert data["version"] == rocm.ROCM_LIBS_VERSION
|
||||
|
||||
# Verify progress was reported
|
||||
progress = get_progress_manager().get_progress("rocm-backend")
|
||||
assert progress is not None
|
||||
assert progress["status"] == "complete"
|
||||
assert progress["progress"] == 100.0
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_is_rocm_active(mock_backends_dir, monkeypatch):
|
||||
monkeypatch.setenv("VOICEBOX_BACKEND_VARIANT", "rocm")
|
||||
assert rocm.is_rocm_active() is True
|
||||
|
||||
monkeypatch.setenv("VOICEBOX_BACKEND_VARIANT", "cpu")
|
||||
assert rocm.is_rocm_active() is False
|
||||
|
||||
monkeypatch.delenv("VOICEBOX_BACKEND_VARIANT", raising=False)
|
||||
assert rocm.is_rocm_active() is False
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_delete_rocm_binary(mock_backends_dir, fake_tar_gz):
|
||||
"""Test deleting the ROCm backend directory."""
|
||||
rocm_dir = rocm.get_rocm_dir()
|
||||
rocm_dir.mkdir(parents=True, exist_ok=True)
|
||||
(rocm_dir / "dummy.txt").write_text("hello")
|
||||
|
||||
result = await rocm.delete_rocm_binary()
|
||||
assert result is True
|
||||
assert not rocm_dir.exists()
|
||||
|
||||
# Deleting again should return False
|
||||
result = await rocm.delete_rocm_binary()
|
||||
assert result is False
|
||||
@@ -0,0 +1,130 @@
|
||||
"""
|
||||
Phase 1.1 Test: ROCm requirements installation.
|
||||
|
||||
Validates that requirements-rocm.txt correctly installs ROCm-enabled PyTorch
|
||||
and that torch.cuda.is_available() returns True on AMD hardware.
|
||||
|
||||
Usage:
|
||||
python -m pytest backend/tests/test_rocm_requirements.py -v
|
||||
"""
|
||||
|
||||
import os
|
||||
import platform
|
||||
import subprocess
|
||||
import sys
|
||||
import tempfile
|
||||
from pathlib import Path
|
||||
|
||||
import pytest
|
||||
|
||||
|
||||
def _has_amd_hardware():
|
||||
"""Check if AMD GPU hardware is present on Windows."""
|
||||
if platform.system() != "Windows":
|
||||
return False
|
||||
try:
|
||||
result = subprocess.run(
|
||||
[
|
||||
"powershell",
|
||||
"-Command",
|
||||
"Get-WmiObject Win32_VideoController | "
|
||||
"Where-Object {$_.AdapterCompatibility -like '*AMD*'} | "
|
||||
"Measure-Object | Select-Object -ExpandProperty Count",
|
||||
],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
check=True,
|
||||
)
|
||||
return int(result.stdout.strip()) > 0
|
||||
except Exception:
|
||||
return False
|
||||
|
||||
|
||||
@pytest.fixture()
|
||||
def backend_dir():
|
||||
return Path(__file__).parent.parent
|
||||
|
||||
|
||||
class TestRocmRequirements:
|
||||
"""Validate requirements-rocm.txt content and installation."""
|
||||
|
||||
def test_requirements_file_exists(self, backend_dir):
|
||||
req_file = backend_dir / "requirements-rocm.txt"
|
||||
assert req_file.exists(), "requirements-rocm.txt must exist"
|
||||
|
||||
def test_requirements_file_content(self, backend_dir):
|
||||
import re
|
||||
req_file = backend_dir / "requirements-rocm.txt"
|
||||
content = req_file.read_text()
|
||||
assert "rocm7.2" in content, "Must point to ROCm 7.2 extra index"
|
||||
# Parse exact package names to avoid false positives from URL substrings
|
||||
package_names = re.findall(r"^([A-Za-z][A-Za-z0-9_-]*)", content, re.MULTILINE)
|
||||
assert "torch" in package_names, "Must include torch package"
|
||||
assert "torchaudio" in package_names, "Must include torchaudio package"
|
||||
assert "torchvision" in package_names, "Must include torchvision package"
|
||||
|
||||
@pytest.mark.timeout(900)
|
||||
@pytest.mark.skipif(
|
||||
not os.environ.get("VOICEBOX_TEST_ROCM_INSTALL"),
|
||||
reason="Set VOICEBOX_TEST_ROCM_INSTALL=1 to run the heavy install test",
|
||||
)
|
||||
def test_rocm_torch_installs_and_detects_amd(self, backend_dir):
|
||||
"""
|
||||
Create a temporary venv, install requirements-rocm.txt, and verify
|
||||
torch.cuda.is_available() returns True on AMD hardware.
|
||||
"""
|
||||
req_file = backend_dir / "requirements-rocm.txt"
|
||||
has_amd = _has_amd_hardware()
|
||||
|
||||
with tempfile.TemporaryDirectory() as tmpdir:
|
||||
venv_dir = Path(tmpdir) / "venv"
|
||||
subprocess.run(
|
||||
[sys.executable, "-m", "venv", str(venv_dir)],
|
||||
check=True,
|
||||
)
|
||||
|
||||
if sys.platform == "win32":
|
||||
venv_python = venv_dir / "Scripts" / "python.exe"
|
||||
else:
|
||||
venv_python = venv_dir / "bin" / "python"
|
||||
|
||||
# Upgrade pip to avoid resolver issues
|
||||
subprocess.run(
|
||||
[str(venv_python), "-m", "pip", "install", "--upgrade", "pip"],
|
||||
check=True,
|
||||
)
|
||||
|
||||
# Install ROCm requirements
|
||||
subprocess.run(
|
||||
[str(venv_python), "-m", "pip", "install", "-r", str(req_file)],
|
||||
check=True,
|
||||
)
|
||||
|
||||
# Verify torch imports and cuda availability
|
||||
result = subprocess.run(
|
||||
[
|
||||
str(venv_python),
|
||||
"-c",
|
||||
"import torch; print(torch.__version__); print(torch.cuda.is_available())",
|
||||
],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
check=True,
|
||||
)
|
||||
|
||||
lines = result.stdout.strip().splitlines()
|
||||
assert len(lines) >= 2, f"Unexpected output: {result.stdout}"
|
||||
torch_version = lines[0]
|
||||
cuda_available = lines[1] == "True"
|
||||
|
||||
# The honest test: on AMD hardware ROCm torch should report cuda available
|
||||
if has_amd:
|
||||
assert cuda_available, (
|
||||
f"AMD hardware detected but torch.cuda.is_available() returned False. "
|
||||
f"torch version: {torch_version}, stderr: {result.stderr}"
|
||||
)
|
||||
else:
|
||||
assert not cuda_available, (
|
||||
f"No AMD hardware detected but torch.cuda.is_available() returned True. "
|
||||
f"torch version: {torch_version}"
|
||||
)
|
||||
@@ -3,19 +3,72 @@ Platform detection for backend selection.
|
||||
"""
|
||||
|
||||
import platform
|
||||
import subprocess
|
||||
from functools import lru_cache
|
||||
from typing import Literal
|
||||
|
||||
|
||||
def is_apple_silicon() -> bool:
|
||||
"""
|
||||
Check if running on Apple Silicon (arm64 macOS).
|
||||
|
||||
|
||||
Returns:
|
||||
True if on Apple Silicon, False otherwise
|
||||
"""
|
||||
return platform.system() == "Darwin" and platform.machine() == "arm64"
|
||||
|
||||
|
||||
@lru_cache(maxsize=1)
|
||||
def is_amd_gpu_windows() -> bool:
|
||||
"""
|
||||
Check if the primary GPU on Windows is an AMD Radeon card.
|
||||
|
||||
Uses WMI to query Win32_VideoController, with a fallback to
|
||||
torch.cuda.get_device_name(0) if WMI is unavailable. This is
|
||||
useful for deciding whether the ROCm backend is appropriate.
|
||||
|
||||
Result is cached since it shells out to PowerShell and the GPU
|
||||
does not change at runtime — safe to call from the health path.
|
||||
|
||||
Returns:
|
||||
True if an AMD GPU is detected on Windows, False otherwise.
|
||||
"""
|
||||
if platform.system() != "Windows":
|
||||
return False
|
||||
|
||||
# Primary method: WMI query for AMD adapters
|
||||
try:
|
||||
result = subprocess.run(
|
||||
[
|
||||
"powershell",
|
||||
"-Command",
|
||||
"Get-CimInstance Win32_VideoController | "
|
||||
"Where-Object {$_.AdapterCompatibility -like '*AMD*'} | "
|
||||
"Measure-Object | Select-Object -ExpandProperty Count",
|
||||
],
|
||||
capture_output=True,
|
||||
text=True,
|
||||
check=True,
|
||||
)
|
||||
if int(result.stdout.strip()) > 0:
|
||||
return True
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
# Fallback: torch.cuda.get_device_name(0) (works for ROCm/HIP too)
|
||||
try:
|
||||
import torch
|
||||
|
||||
if torch.cuda.is_available():
|
||||
name = torch.cuda.get_device_name(0)
|
||||
if "Radeon" in name or "AMD" in name:
|
||||
return True
|
||||
except Exception:
|
||||
pass
|
||||
|
||||
return False
|
||||
|
||||
|
||||
def get_backend_type() -> Literal["mlx", "pytorch"]:
|
||||
"""
|
||||
Detect the best backend for the current platform.
|
||||
|
||||
@@ -0,0 +1,251 @@
|
||||
"""
|
||||
Package the PyInstaller --onedir ROCm build into two archives.
|
||||
|
||||
Takes the PyInstaller --onedir output directory and splits it into:
|
||||
1. voicebox-server-rocm.tar.gz — server core (exe + non-AMD deps)
|
||||
2. rocm-libs-{version}.tar.gz — AMD/ROCm runtime libraries only
|
||||
3. rocm-libs.json — version manifest for the ROCm libs
|
||||
|
||||
Mirrors scripts/package_cuda.py. The split lets the server core re-download on
|
||||
every app update while the much larger ROCm runtime stays cached until the
|
||||
toolkit version bumps.
|
||||
|
||||
Usage:
|
||||
python scripts/package_rocm.py backend/dist/voicebox-server-rocm/
|
||||
python scripts/package_rocm.py backend/dist/voicebox-server-rocm/ --output release-assets/
|
||||
python scripts/package_rocm.py backend/dist/voicebox-server-rocm/ --rocm-libs-version rocm7.2-v1
|
||||
"""
|
||||
|
||||
import argparse
|
||||
import hashlib
|
||||
import json
|
||||
import sys
|
||||
import tarfile
|
||||
from pathlib import Path
|
||||
|
||||
# DLL/.so name prefixes that identify AMD ROCm/HIP runtime libraries. They may
|
||||
# sit in torch/lib/ (torch's bundled HIP runtime) or inside the bundled ROCm SDK
|
||||
# packages. Matched case-insensitively against the file's base name.
|
||||
ROCM_DLL_PREFIXES = (
|
||||
"amdhip",
|
||||
"amd_comgr",
|
||||
"amdocl",
|
||||
"hiprtc",
|
||||
"hipblaslt",
|
||||
"hipblas",
|
||||
"hipfft",
|
||||
"hiprand",
|
||||
"hipsolver",
|
||||
"hipsparse",
|
||||
"hip",
|
||||
"rocblas",
|
||||
"rocfft",
|
||||
"rocrand",
|
||||
"rocsolver",
|
||||
"rocsparse",
|
||||
"rocprofiler",
|
||||
"roctracer",
|
||||
"roctx",
|
||||
"rocm_smi",
|
||||
"miopen",
|
||||
"rccl",
|
||||
"hsa-runtime",
|
||||
"hsa",
|
||||
)
|
||||
|
||||
# Directory markers for the bundled ROCm SDK runtime packages. Everything under
|
||||
# these trees except Python sources (the pure-python rocm_sdk glue) is part of
|
||||
# the runtime payload — this is where rocBLAS Tensile data and MIOpen kernel
|
||||
# databases live, which dominate the download size.
|
||||
ROCM_LIB_DIR_MARKERS = (
|
||||
"_rocm_sdk_core",
|
||||
"_rocm_sdk_libraries_custom",
|
||||
"rocm_sdk_core",
|
||||
"rocm_sdk_libraries_custom",
|
||||
)
|
||||
|
||||
# Heavy native/data extensions shipped by the ROCm runtime (HIP fat binaries,
|
||||
# rocBLAS Tensile data, MIOpen kernel DBs).
|
||||
ROCM_LIB_EXTS = (".dll", ".so", ".dat", ".db", ".kdb", ".hsaco", ".co", ".bc")
|
||||
|
||||
# Python sources stay in the server core so the rocm_sdk import glue remains
|
||||
# alongside the exe. (Both archives extract into backends/rocm/, so this only
|
||||
# affects which archive carries the file, not runtime resolution.)
|
||||
_PYTHON_EXTS = (".py", ".pyc", ".pyi")
|
||||
|
||||
|
||||
def is_rocm_file(rel_path: str) -> bool:
|
||||
"""Check if a relative path belongs to the AMD ROCm runtime libraries.
|
||||
|
||||
Identifies large ROCm/HIP runtime DLLs and the SDK runtime payload
|
||||
(kernel databases, Tensile data) regardless of where PyInstaller placed
|
||||
them, while keeping pure-python glue in the server core.
|
||||
"""
|
||||
rel_lower = rel_path.lower().replace("\\", "/")
|
||||
name = rel_lower.rsplit("/", 1)[-1]
|
||||
|
||||
# Never split out Python sources / stubs.
|
||||
if name.endswith(_PYTHON_EXTS):
|
||||
return False
|
||||
|
||||
# Native payload inside the bundled ROCm SDK package trees.
|
||||
if any(marker in rel_lower for marker in ROCM_LIB_DIR_MARKERS):
|
||||
if name.endswith(ROCM_LIB_EXTS):
|
||||
return True
|
||||
|
||||
# ROCm/HIP DLLs/shared objects anywhere (e.g. _internal/torch/lib/amdhip64.dll).
|
||||
if name.endswith((".dll", ".so")):
|
||||
name_no_ext = name.rsplit(".", 1)[0]
|
||||
for prefix in ROCM_DLL_PREFIXES:
|
||||
if name_no_ext.startswith(prefix):
|
||||
return True
|
||||
|
||||
return False
|
||||
|
||||
|
||||
def sha256_file(path: Path) -> str:
|
||||
"""Compute SHA-256 hex digest of a file."""
|
||||
h = hashlib.sha256()
|
||||
with open(path, "rb") as f:
|
||||
while True:
|
||||
chunk = f.read(1024 * 1024)
|
||||
if not chunk:
|
||||
break
|
||||
h.update(chunk)
|
||||
return h.hexdigest()
|
||||
|
||||
|
||||
def package(
|
||||
onedir_path: Path,
|
||||
output_dir: Path,
|
||||
rocm_libs_version: str,
|
||||
torch_compat: str,
|
||||
):
|
||||
output_dir.mkdir(parents=True, exist_ok=True)
|
||||
|
||||
# Collect all files in the onedir output, split into core vs rocm.
|
||||
core_files = []
|
||||
rocm_files = []
|
||||
|
||||
for item in sorted(onedir_path.rglob("*")):
|
||||
if item.is_dir():
|
||||
continue
|
||||
rel = item.relative_to(onedir_path)
|
||||
rel_str = str(rel)
|
||||
if is_rocm_file(rel_str):
|
||||
rocm_files.append((rel_str, item))
|
||||
else:
|
||||
core_files.append((rel_str, item))
|
||||
|
||||
core_size = sum(f.stat().st_size for _, f in core_files)
|
||||
rocm_size = sum(f.stat().st_size for _, f in rocm_files)
|
||||
|
||||
print(f"Input directory: {onedir_path}")
|
||||
print(f"Core files: {len(core_files)} ({core_size / (1024**2):.1f} MB)")
|
||||
print(f"ROCm files: {len(rocm_files)} ({rocm_size / (1024**2):.1f} MB)")
|
||||
|
||||
if not rocm_files:
|
||||
print(
|
||||
f"ERROR: No ROCm files found in {onedir_path}. "
|
||||
"Refusing to create an empty ROCm libs archive.",
|
||||
file=sys.stderr,
|
||||
)
|
||||
print(
|
||||
"Make sure you built with --rocm and the ROCm SDK packages are present. "
|
||||
"If the layout differs, adjust ROCM_DLL_PREFIXES / ROCM_LIB_DIR_MARKERS.",
|
||||
file=sys.stderr,
|
||||
)
|
||||
sys.exit(1)
|
||||
|
||||
# Create server core archive. Files are stored relative to the archive root
|
||||
# (no parent prefix) so extracting to backends/rocm/ lands at the right level.
|
||||
server_archive = output_dir / "voicebox-server-rocm.tar.gz"
|
||||
print(f"\nCreating server core archive: {server_archive.name}")
|
||||
with tarfile.open(server_archive, "w:gz") as tar:
|
||||
for rel_str, full_path in core_files:
|
||||
tar.add(full_path, arcname=rel_str)
|
||||
server_sha = sha256_file(server_archive)
|
||||
(output_dir / "voicebox-server-rocm.tar.gz.sha256").write_text(
|
||||
f"{server_sha} voicebox-server-rocm.tar.gz\n"
|
||||
)
|
||||
print(f" Size: {server_archive.stat().st_size / (1024**2):.1f} MB")
|
||||
print(f" SHA-256: {server_sha[:16]}...")
|
||||
|
||||
# Create ROCm libs archive.
|
||||
rocm_libs_archive = output_dir / f"rocm-libs-{rocm_libs_version}.tar.gz"
|
||||
print(f"\nCreating ROCm libs archive: {rocm_libs_archive.name}")
|
||||
with tarfile.open(rocm_libs_archive, "w:gz") as tar:
|
||||
for rel_str, full_path in rocm_files:
|
||||
tar.add(full_path, arcname=rel_str)
|
||||
rocm_sha = sha256_file(rocm_libs_archive)
|
||||
(output_dir / f"rocm-libs-{rocm_libs_version}.tar.gz.sha256").write_text(
|
||||
f"{rocm_sha} rocm-libs-{rocm_libs_version}.tar.gz\n"
|
||||
)
|
||||
print(f" Size: {rocm_libs_archive.stat().st_size / (1024**2):.1f} MB")
|
||||
print(f" SHA-256: {rocm_sha[:16]}...")
|
||||
|
||||
# Write rocm-libs.json manifest.
|
||||
manifest = {
|
||||
"version": rocm_libs_version,
|
||||
"torch_compat": torch_compat,
|
||||
"archive": rocm_libs_archive.name,
|
||||
"sha256": rocm_sha,
|
||||
}
|
||||
manifest_path = output_dir / "rocm-libs.json"
|
||||
manifest_path.write_text(json.dumps(manifest, indent=2) + "\n")
|
||||
print(f"\nManifest: {manifest_path.name}")
|
||||
print(json.dumps(manifest, indent=2))
|
||||
|
||||
# Summary
|
||||
total_input = core_size + rocm_size
|
||||
total_output = server_archive.stat().st_size + rocm_libs_archive.stat().st_size
|
||||
print(f"\nTotal input: {total_input / (1024**3):.2f} GB")
|
||||
print(f"Total output: {total_output / (1024**3):.2f} GB (compressed)")
|
||||
print(
|
||||
f"Server core: {server_archive.stat().st_size / (1024**2):.1f} MB (redownloaded on app update)"
|
||||
)
|
||||
print(
|
||||
f"ROCm libs: {rocm_libs_archive.stat().st_size / (1024**2):.1f} MB (cached until ROCm toolkit bump)"
|
||||
)
|
||||
|
||||
|
||||
def main():
|
||||
parser = argparse.ArgumentParser(
|
||||
description="Package PyInstaller --onedir ROCm build into server + ROCm libs archives"
|
||||
)
|
||||
parser.add_argument(
|
||||
"input",
|
||||
type=Path,
|
||||
help="Path to PyInstaller --onedir output directory (e.g. backend/dist/voicebox-server-rocm/)",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--output",
|
||||
type=Path,
|
||||
default=None,
|
||||
help="Output directory for archives (default: same as input parent)",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--rocm-libs-version",
|
||||
type=str,
|
||||
default="rocm7.2-v1",
|
||||
help="Version string for the ROCm libs archive (default: rocm7.2-v1)",
|
||||
)
|
||||
parser.add_argument(
|
||||
"--torch-compat",
|
||||
type=str,
|
||||
default=">=2.9.0,<2.10.0",
|
||||
help="Torch version compatibility range (default: >=2.9.0,<2.10.0)",
|
||||
)
|
||||
args = parser.parse_args()
|
||||
|
||||
if not args.input.is_dir():
|
||||
print(f"Error: {args.input} is not a directory", file=sys.stderr)
|
||||
print("Expected a PyInstaller --onedir output directory.", file=sys.stderr)
|
||||
sys.exit(1)
|
||||
|
||||
output_dir = args.output or args.input.parent
|
||||
package(args.input, output_dir, args.rocm_libs_version, args.torch_compat)
|
||||
|
||||
|
||||
if __name__ == "__main__":
|
||||
main()
|
||||
+188
-39
@@ -200,6 +200,63 @@ struct ServerState {
|
||||
server_pid: Mutex<Option<u32>>,
|
||||
keep_running_on_close: Mutex<bool>,
|
||||
models_dir: Mutex<Option<String>>,
|
||||
/// Override the backend selection: Some("cpu") forces the CPU sidecar even
|
||||
/// when GPU binaries exist (solving the Windows catch-22 where an active
|
||||
/// .exe cannot be deleted), while Some("cuda")/Some("rocm") pin a specific
|
||||
/// GPU variant when more than one is installed. None uses the on-disk
|
||||
/// default (ROCm preferred, then CUDA). Persisted to disk so the choice
|
||||
/// survives an app restart.
|
||||
backend_override: Mutex<Option<String>>,
|
||||
}
|
||||
|
||||
fn backend_override_file(data_dir: &std::path::Path) -> std::path::PathBuf {
|
||||
data_dir.join("backend_override")
|
||||
}
|
||||
|
||||
fn read_persisted_backend_override(data_dir: &std::path::Path) -> Option<String> {
|
||||
std::fs::read_to_string(backend_override_file(data_dir))
|
||||
.ok()
|
||||
.map(|s| s.trim().to_string())
|
||||
.filter(|s| !s.is_empty())
|
||||
}
|
||||
|
||||
fn write_persisted_backend_override(data_dir: &std::path::Path, value: Option<&str>) {
|
||||
let path = backend_override_file(data_dir);
|
||||
match value {
|
||||
Some(v) => {
|
||||
let _ = std::fs::create_dir_all(data_dir);
|
||||
if let Err(e) = std::fs::write(&path, v) {
|
||||
println!("Failed to persist backend override: {}", e);
|
||||
}
|
||||
}
|
||||
None => {
|
||||
let _ = std::fs::remove_file(&path);
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
/// Run `<exe> --version` with a 10-second timeout to avoid hanging Tauri startup.
|
||||
/// Returns the last whitespace-delimited token from stdout (e.g. "0.4.4"), or None on any failure.
|
||||
async fn probe_binary_version(exe: &std::path::Path, cwd: &std::path::Path) -> Option<String> {
|
||||
let mut cmd = tokio::process::Command::new(exe);
|
||||
cmd.arg("--version")
|
||||
.current_dir(cwd)
|
||||
.kill_on_drop(true);
|
||||
|
||||
match tokio::time::timeout(std::time::Duration::from_secs(10), cmd.output()).await {
|
||||
Ok(Ok(output)) => {
|
||||
let s = String::from_utf8_lossy(&output.stdout);
|
||||
s.trim().split_whitespace().last().map(String::from)
|
||||
}
|
||||
Ok(Err(e)) => {
|
||||
println!("Version probe failed: {}", e);
|
||||
None
|
||||
}
|
||||
Err(_) => {
|
||||
println!("Version probe timed out after 10s");
|
||||
None
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
#[command]
|
||||
@@ -360,6 +417,45 @@ async fn start_server(
|
||||
println!("Data directory: {:?}", data_dir);
|
||||
println!("Remote mode: {}", remote.unwrap_or(false));
|
||||
|
||||
// Check for ROCm backend in data directory (onedir layout: backends/rocm/)
|
||||
let rocm_binary = {
|
||||
let rocm_dir = data_dir.join("backends").join("rocm");
|
||||
let rocm_name = if cfg!(windows) {
|
||||
"voicebox-server-rocm.exe"
|
||||
} else {
|
||||
"voicebox-server-rocm"
|
||||
};
|
||||
let exe_path = rocm_dir.join(rocm_name);
|
||||
if exe_path.exists() {
|
||||
println!("Found ROCm backend at {:?}", rocm_dir);
|
||||
|
||||
let app_version = app.config().version.clone().unwrap_or_default();
|
||||
let binary_version = probe_binary_version(&exe_path, &rocm_dir).await;
|
||||
let version_ok = if !app_version.is_empty()
|
||||
&& binary_version.as_deref() == Some(app_version.as_str())
|
||||
{
|
||||
println!("ROCm binary version {} matches app version", app_version);
|
||||
true
|
||||
} else {
|
||||
println!(
|
||||
"ROCm binary version mismatch: binary={}, app={}. Falling back to CPU.",
|
||||
binary_version.as_deref().unwrap_or("<unknown>"),
|
||||
app_version
|
||||
);
|
||||
false
|
||||
};
|
||||
|
||||
if version_ok {
|
||||
Some(exe_path)
|
||||
} else {
|
||||
None
|
||||
}
|
||||
} else {
|
||||
println!("No ROCm backend found");
|
||||
None
|
||||
}
|
||||
};
|
||||
|
||||
// Check for CUDA backend in data directory (onedir layout: backends/cuda/)
|
||||
let cuda_binary = {
|
||||
let cuda_dir = data_dir.join("backends").join("cuda");
|
||||
@@ -375,30 +471,19 @@ async fn start_server(
|
||||
// Version check: run --version from the onedir directory so
|
||||
// PyInstaller can find its support files for the fast --version path
|
||||
let app_version = app.config().version.clone().unwrap_or_default();
|
||||
let version_ok = match std::process::Command::new(&exe_path)
|
||||
.arg("--version")
|
||||
.current_dir(&cuda_dir)
|
||||
.output()
|
||||
let binary_version = probe_binary_version(&exe_path, &cuda_dir).await;
|
||||
let version_ok = if !app_version.is_empty()
|
||||
&& binary_version.as_deref() == Some(app_version.as_str())
|
||||
{
|
||||
Ok(output) => {
|
||||
// Output format: "voicebox-server X.Y.Z\n"
|
||||
let version_str = String::from_utf8_lossy(&output.stdout);
|
||||
let binary_version = version_str.trim().split_whitespace().last().unwrap_or("");
|
||||
if binary_version == app_version {
|
||||
println!("CUDA binary version {} matches app version", binary_version);
|
||||
true
|
||||
} else {
|
||||
println!(
|
||||
"CUDA binary version mismatch: binary={}, app={}. Falling back to CPU.",
|
||||
binary_version, app_version
|
||||
);
|
||||
false
|
||||
}
|
||||
}
|
||||
Err(e) => {
|
||||
println!("Failed to check CUDA binary version: {}. Falling back to CPU.", e);
|
||||
false
|
||||
}
|
||||
println!("CUDA binary version {} matches app version", app_version);
|
||||
true
|
||||
} else {
|
||||
println!(
|
||||
"CUDA binary version mismatch: binary={}, app={}. Falling back to CPU.",
|
||||
binary_version.as_deref().unwrap_or("<unknown>"),
|
||||
app_version
|
||||
);
|
||||
false
|
||||
};
|
||||
|
||||
if version_ok {
|
||||
@@ -465,24 +550,74 @@ async fn start_server(
|
||||
println!("Custom models directory: {}", dir);
|
||||
}
|
||||
|
||||
// Respect backend override (e.g., user wants CPU even though a GPU binary
|
||||
// exists, or pinned a specific GPU variant). The in-memory value resets to
|
||||
// None on app launch, so fall back to the persisted choice on disk.
|
||||
let backend_override = {
|
||||
let in_memory = state.backend_override.lock().unwrap().clone();
|
||||
in_memory.or_else(|| read_persisted_backend_override(&data_dir))
|
||||
};
|
||||
|
||||
// Honor a pinned GPU variant by ignoring the other one — but only when the
|
||||
// pinned variant is actually installed, so a stale pin to a deleted backend
|
||||
// self-heals to the default order instead of forcing CPU. With no pin, both
|
||||
// stay eligible and the launch order below prefers ROCm, then CUDA.
|
||||
let pin = backend_override.as_deref();
|
||||
let pin_cuda = pin == Some("cuda") && cuda_binary.is_some();
|
||||
let pin_rocm = pin == Some("rocm") && rocm_binary.is_some();
|
||||
let rocm_binary = if pin_cuda { None } else { rocm_binary };
|
||||
let cuda_binary = if pin_rocm { None } else { cuda_binary };
|
||||
|
||||
// If ROCm binary exists, launch it from the onedir directory.
|
||||
// If CUDA binary exists, launch it from the onedir directory.
|
||||
// .current_dir() is critical: PyInstaller onedir expects all DLLs and
|
||||
// support files (nvidia/, _internal/, etc.) relative to the exe.
|
||||
let spawn_result = if let Some(ref cuda_path) = cuda_binary {
|
||||
let cuda_dir = cuda_path.parent().unwrap();
|
||||
println!("Launching CUDA backend: {:?} (cwd: {:?})", cuda_path, cuda_dir);
|
||||
let mut cmd = app.shell().command(cuda_path.to_str().unwrap());
|
||||
cmd = cmd.current_dir(cuda_dir);
|
||||
cmd = cmd.args(["--data-dir", &data_dir_str, "--port", &port_str, "--parent-pid", &parent_pid_str]);
|
||||
if is_remote {
|
||||
cmd = cmd.args(["--host", "0.0.0.0"]);
|
||||
// support files relative to the exe.
|
||||
let spawn_result = if backend_override.as_deref() != Some("cpu") {
|
||||
let mut gpu_spawn = None;
|
||||
|
||||
if let Some(ref rocm_path) = rocm_binary {
|
||||
let rocm_dir = rocm_path.parent().unwrap();
|
||||
println!("Launching ROCm backend: {:?} (cwd: {:?})", rocm_path, rocm_dir);
|
||||
let mut cmd = app.shell().command(rocm_path.to_str().unwrap());
|
||||
cmd = cmd.current_dir(rocm_dir);
|
||||
cmd = cmd.args(["--data-dir", &data_dir_str, "--port", &port_str, "--parent-pid", &parent_pid_str]);
|
||||
if is_remote { cmd = cmd.args(["--host", "0.0.0.0"]); }
|
||||
if let Some(ref dir) = effective_models_dir { cmd = cmd.env("VOICEBOX_MODELS_DIR", dir); }
|
||||
match cmd.spawn() {
|
||||
Ok(r) => { gpu_spawn = Some(Ok(r)); }
|
||||
Err(e) => { println!("ROCm spawn failed ({}), trying CUDA/CPU fallback", e); }
|
||||
}
|
||||
}
|
||||
if let Some(ref dir) = effective_models_dir {
|
||||
cmd = cmd.env("VOICEBOX_MODELS_DIR", dir);
|
||||
|
||||
if gpu_spawn.is_none() {
|
||||
if let Some(ref cuda_path) = cuda_binary {
|
||||
let cuda_dir = cuda_path.parent().unwrap();
|
||||
println!("Launching CUDA backend: {:?} (cwd: {:?})", cuda_path, cuda_dir);
|
||||
let mut cmd = app.shell().command(cuda_path.to_str().unwrap());
|
||||
cmd = cmd.current_dir(cuda_dir);
|
||||
cmd = cmd.args(["--data-dir", &data_dir_str, "--port", &port_str, "--parent-pid", &parent_pid_str]);
|
||||
if is_remote { cmd = cmd.args(["--host", "0.0.0.0"]); }
|
||||
if let Some(ref dir) = effective_models_dir { cmd = cmd.env("VOICEBOX_MODELS_DIR", dir); }
|
||||
match cmd.spawn() {
|
||||
Ok(r) => { gpu_spawn = Some(Ok(r)); }
|
||||
Err(e) => { println!("CUDA spawn failed ({}), falling back to CPU", e); }
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if let Some(result) = gpu_spawn {
|
||||
result
|
||||
} else {
|
||||
// Fall back to bundled CPU sidecar
|
||||
sidecar = sidecar.args(["--data-dir", &data_dir_str, "--port", &port_str, "--parent-pid", &parent_pid_str]);
|
||||
if is_remote { sidecar = sidecar.args(["--host", "0.0.0.0"]); }
|
||||
if let Some(ref dir) = effective_models_dir { sidecar = sidecar.env("VOICEBOX_MODELS_DIR", dir); }
|
||||
println!("Spawning bundled CPU server process...");
|
||||
sidecar.spawn()
|
||||
}
|
||||
cmd.spawn()
|
||||
} else {
|
||||
// Use the bundled CPU sidecar
|
||||
// Override forces CPU — use bundled sidecar, GPU binary stays on disk
|
||||
println!("Backend override=cpu: using bundled CPU sidecar");
|
||||
sidecar = sidecar.args(["--data-dir", &data_dir_str, "--port", &port_str, "--parent-pid", &parent_pid_str]);
|
||||
if is_remote {
|
||||
sidecar = sidecar.args(["--host", "0.0.0.0"]);
|
||||
@@ -490,7 +625,6 @@ async fn start_server(
|
||||
if let Some(ref dir) = effective_models_dir {
|
||||
sidecar = sidecar.env("VOICEBOX_MODELS_DIR", dir);
|
||||
}
|
||||
println!("Spawning server process...");
|
||||
sidecar.spawn()
|
||||
};
|
||||
|
||||
@@ -762,9 +896,9 @@ async fn restart_server(
|
||||
println!("restart_server: waiting for port release...");
|
||||
tokio::time::sleep(tokio::time::Duration::from_millis(1000)).await;
|
||||
|
||||
// Start server again (will auto-detect CUDA binary and use stored models_dir)
|
||||
// Start server again (will auto-detect GPU binary and use stored models_dir)
|
||||
println!("restart_server: starting server...");
|
||||
start_server(app, state, None, None).await
|
||||
start_server(app, state.clone(), None, None).await
|
||||
}
|
||||
|
||||
#[command]
|
||||
@@ -773,6 +907,19 @@ fn set_keep_server_running(state: State<'_, ServerState>, keep_running: bool) {
|
||||
*state.keep_running_on_close.lock().unwrap() = keep_running;
|
||||
}
|
||||
|
||||
#[command]
|
||||
fn set_backend_override(
|
||||
app: tauri::AppHandle,
|
||||
state: State<'_, ServerState>,
|
||||
backend: Option<String>,
|
||||
) {
|
||||
println!("set_backend_override called with: {:?}", backend);
|
||||
if let Ok(data_dir) = app.path().app_data_dir() {
|
||||
write_persisted_backend_override(&data_dir, backend.as_deref());
|
||||
}
|
||||
*state.backend_override.lock().unwrap() = backend;
|
||||
}
|
||||
|
||||
#[command]
|
||||
async fn start_system_audio_capture(
|
||||
state: State<'_, audio_capture::AudioCaptureState>,
|
||||
@@ -1239,6 +1386,7 @@ pub fn run() {
|
||||
server_pid: Mutex::new(None),
|
||||
keep_running_on_close: Mutex::new(false),
|
||||
models_dir: Mutex::new(None),
|
||||
backend_override: Mutex::new(None),
|
||||
})
|
||||
.manage(audio_capture::AudioCaptureState::new())
|
||||
.manage(audio_output::AudioOutputState::new())
|
||||
@@ -1357,6 +1505,7 @@ pub fn run() {
|
||||
stop_server,
|
||||
restart_server,
|
||||
set_keep_server_running,
|
||||
set_backend_override,
|
||||
start_system_audio_capture,
|
||||
stop_system_audio_capture,
|
||||
is_system_audio_supported,
|
||||
|
||||
@@ -52,6 +52,15 @@ class TauriLifecycle implements PlatformLifecycle {
|
||||
}
|
||||
}
|
||||
|
||||
async setBackendOverride(backend?: string | null): Promise<void> {
|
||||
try {
|
||||
await invoke('set_backend_override', { backend: backend ?? undefined });
|
||||
} catch (error) {
|
||||
console.error('Failed to set backend override:', error);
|
||||
throw error;
|
||||
}
|
||||
}
|
||||
|
||||
async setupWindowCloseHandler(): Promise<void> {
|
||||
try {
|
||||
// Listen for window close request from Rust
|
||||
|
||||
@@ -24,6 +24,10 @@ class WebLifecycle implements PlatformLifecycle {
|
||||
// No-op for web
|
||||
}
|
||||
|
||||
async setBackendOverride(_backend?: string | null): Promise<void> {
|
||||
// No-op for web - backend variant is managed externally
|
||||
}
|
||||
|
||||
async setupWindowCloseHandler(): Promise<void> {
|
||||
// No-op for web - no window close handling needed
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user