mirror of
https://github.com/JezzWTF/vibepod.git
synced 2026-06-13 03:58:07 +00:00
Claude
bb6da662de
Introduces a third hardware mode alongside CUDA and CPU: ROCm (AMD GPU). AMD GPUs present as CUDA devices under PyTorch ROCm, so the existing GPU path is reused with minimal changes — the main additions are wheel management, device detection, and suppressing flash_attn (unsupported on ROCm). - server/vibevoice_server.py: extend _resolve_device() to recognise 'rocm' (auto-detected via torch.version.hip); add _torch_device() helper that maps 'rocm' → 'cuda' for all PyTorch API calls; apply GPU optimisations for both cuda and rocm in _init_model(); always use sdpa on ROCm; propagate _torch_device() to _load_voice_presets() map_location. - server/start.sh: add --rocm flag; sync .venv-rocm with uv sync --no-sources then replace torch with the ROCm 6.2 wheel via uv pip install; set VIBEPOD_DEVICE=rocm for uvicorn. - server/pyproject.toml: register pytorch-rocm62 index (explicit); add .venv-rocm to ruff excludes. - package.json: add dev:rocm and dev:server:rocm scripts. - README.md: document ROCm mode, prerequisites (RX 6000+, ROCm 6.2+, Linux), and new commands; expand CUDA vs CPU section to CUDA vs CPU vs ROCm. https://claude.ai/code/session_0168pSswiaoEf6LEx6UQWfBu
67 lines
2.0 KiB
TOML
67 lines
2.0 KiB
TOML
[project]
|
|
name = "vibepod-server"
|
|
version = "0.1.0"
|
|
description = "VibePod TTS Server — VibeVoice FastAPI backend"
|
|
requires-python = ">=3.10"
|
|
dependencies = [
|
|
# torch is listed explicitly so uv pulls the CUDA wheel (see [tool.uv.sources]).
|
|
# To switch back to CPU-only, remove the [tool.uv.sources] torch entry below.
|
|
"torch>=2.0.0",
|
|
# VibeVoice custom model + processor classes (not yet in upstream transformers)
|
|
# Uses JezzWTF/VibeVoice fork so VibePod-specific optimisations land here.
|
|
"vibevoice @ git+https://github.com/JezzWTF/VibeVoice.git",
|
|
# Exact version required by vibevoice's streaming TTS module
|
|
"transformers==4.51.3",
|
|
"fastapi>=0.111.0",
|
|
"uvicorn[standard]>=0.29.0",
|
|
"soundfile>=0.12.1",
|
|
"pydantic>=2.7.0",
|
|
"huggingface_hub>=0.23.0",
|
|
]
|
|
|
|
[dependency-groups]
|
|
dev = [
|
|
"ruff>=0.11.0",
|
|
]
|
|
|
|
# No build-system — this is a scripts project, not an installable package.
|
|
# Lock file is committed so installs are reproducible.
|
|
# Run `uv lock --upgrade` to bump dependencies.
|
|
|
|
[tool.ruff]
|
|
line-length = 100
|
|
indent-width = 4
|
|
target-version = "py310"
|
|
exclude = [".git", ".venv", ".venv-cpu", ".venv-rocm", "__pycache__"]
|
|
|
|
[tool.ruff.lint]
|
|
select = ["E", "F", "UP", "B", "SIM", "I"]
|
|
ignore = [
|
|
"E501", # line-too-long — handled by formatter
|
|
"B905", # zip() without strict= — existing code, lengths are known-correct
|
|
]
|
|
|
|
[tool.ruff.lint.per-file-ignores]
|
|
"download_model.py" = ["T201"] # allow print statements in CLI scripts
|
|
|
|
[tool.ruff.format]
|
|
quote-style = "double"
|
|
indent-style = "space"
|
|
line-ending = "lf"
|
|
|
|
[[tool.uv.index]]
|
|
name = "pytorch-cu124"
|
|
url = "https://download.pytorch.org/whl/cu124"
|
|
explicit = true
|
|
|
|
[[tool.uv.index]]
|
|
name = "pytorch-rocm62"
|
|
url = "https://download.pytorch.org/whl/rocm6.2"
|
|
explicit = true
|
|
|
|
[tool.uv.sources]
|
|
# Pull torch from the PyTorch CUDA 12.4 index instead of PyPI's CPU-only wheel.
|
|
# CUDA 12.4 runs on any driver >= 525.60 (RTX 30/40 series all qualify).
|
|
# To use CPU instead: remove this block and run `uv sync --reinstall-package torch`.
|
|
torch = { index = "pytorch-cu124" }
|