mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-15 04:40:40 -07:00
e766c7cbfb
* feat(windows): add native ROCm support for AMD GPUs Implements native ROCm architecture for Windows. - Adds backend build pipeline for voicebox-server-rocm.exe - Detects AMD GPUs dynamically and routes PyTorch allocations - Adds automatic download and update logic for ROCm dependencies - Refactors UI in GpuPage.tsx and GpuAcceleration.tsx to add AMD flows - Fixes 'Switch to CPU' lock on Windows via Tauri backend_override state - Resolves PyInstaller/rocm_sdk UnboundLocalError silent crashes - Resolves Numba/NumPy 2.x incompatibilities during Qwen3-TTS load - Resolves HF_HUB_OFFLINE Catch-22 for CustomVoice processor caching * fix(rocm): host libs archive under the app release tag, drop offline-load regression Align the ROCm libs download with the CUDA pattern: both the server core and the libs archive are published under the app-version release tag, with the libs content version encoded in the filename only. The previous code fetched libs from a separate rocm7.2-v1 tag, which disagreed with the download test. Also revert the unrelated Qwen CustomVoice changes that wrapped model loading in force_offline_if_cached (not imported — a NameError on load for every platform) and re-added a Base-model cache gate. The inference-path offline guard was deliberately removed previously. * feat(rocm): gate download on AMD detection and persist the backend variant The ROCm download section now only shows when the backend reports an AMD GPU on Windows (new supports_rocm health field, backed by the memoized is_amd_gpu_windows detection that was previously unused), or when ROCm is already downloaded/active. Make the backend override honor a pinned variant: set_backend_override persists the choice to disk so it survives an app restart, start_server reads it back, and a cuda/rocm pin now actually selects that variant instead of always preferring ROCm. A stale pin to a deleted backend self-heals to the default order rather than forcing CPU. Add the web no-op stub for the new method. * chore(rocm): drop incomplete vitest harness for the unused GpuAcceleration component GpuAcceleration.tsx is not routed anywhere (GpuPage is the live settings view), and the added vitest setup referenced testing-library/vitest deps that were not in the lockfile, breaking the web typecheck. Remove the dead component's test and its scaffolding to keep this PR scoped to the ROCm feature. * ci(rocm): add ROCm release-artifact pipeline Mirror the CUDA packaging path for ROCm so the runtime download has artifacts to fetch. scripts/package_rocm.py splits the PyInstaller --rocm onedir into voicebox-server-rocm.tar.gz (core) + rocm-libs-rocm7.2-v1.tar.gz (AMD runtime: HIP DLLs, rocBLAS Tensile data, MIOpen kernel DBs) + rocm-libs.json, matching the names services/rocm.py expects, both under the app-version release tag. The new build-rocm-windows job in release.yml builds on windows-latest/cp312 and lets build_binary.py --rocm pull the official AMD Radeon wheels. The file classifier can't be validated against a real AMD build on CI, so it has unit coverage (test_package_rocm.py) against a synthetic onedir layout. The prefixes/dir markers may need a tweak after the first real build on AMD hardware — the packager hard-fails loudly if it classifies zero ROCm files. --------- Co-authored-by: Jamie Pine <[email protected]>
122 lines
4.5 KiB
Python
122 lines
4.5 KiB
Python
"""
|
|
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")
|