feat(windows): Native AMD ROCm GPU Acceleration (Resolves #531) (#538)

* 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
2026-06-30 15:43:18 -07:00
committed by GitHub
co-authored by Jamie Pine
parent c2282b256a
commit e766c7cbfb
32 changed files with 2967 additions and 309 deletions
@@ -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>
+316 -99
View File
@@ -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>
)}