mirror of
https://github.com/jamiepine/voicebox.git
synced 2026-09-15 04:40:40 -07:00
Mike KeyandGitHub
c2282b256a
* Fix ROCm setup for Linux AMD GPUs - Ensure Docker ROCm builds resolve PyTorch packages from the ROCm wheel index so later dependency installs do not replace them with CUDA wheels. - Move ROCm device group handling to a runtime entrypoint that joins the groups owning /dev/kfd and /dev/dri, avoiding distro-specific render/video GID defaults. - Leave HSA_OVERRIDE_GFX_VERSION unset by default in the ROCm compose overlay so newer RDNA GPUs can use native ROCm detection. - Add Linux GPU detection to the Unix setup recipe so AMD systems install ROCm torch wheels and NVIDIA systems install CUDA wheels before backend dependencies. * docs(changelog): add Linux ROCm setup entry * fix(setup): pin ROCm torch wheels and prefer NVIDIA over amdgpu - Install torch/torchaudio from the ROCm index only, before the pooled requirements install, so a plain PyPI (CUDA) wheel can't outrank +rocm - Detect NVIDIA before AMD and gate ROCm on /dev/kfd, so hybrid AMD+NVIDIA hosts get CUDA instead of ROCm
37 lines
1.3 KiB
YAML
37 lines
1.3 KiB
YAML
---
|
|
# ROCm (AMD GPU) overlay for Voicebox
|
|
#
|
|
# docker compose -f docker-compose.yml -f docker-compose.rocm.yml up --build
|
|
#
|
|
# Requires ROCm drivers on the host:
|
|
# https://rocm.docs.amd.com/projects/install-on-linux
|
|
# RDNA4 (RX 9000): export ROCM_VERSION=7.2 (default 6.3 covers RDNA1-3).
|
|
|
|
services:
|
|
voicebox:
|
|
build:
|
|
context: .
|
|
args:
|
|
PYTORCH_VARIANT: rocm
|
|
ROCM_VERSION: ${ROCM_VERSION:-6.3}
|
|
|
|
devices:
|
|
- /dev/kfd
|
|
- /dev/dri
|
|
|
|
environment:
|
|
# HSA_OVERRIDE_GFX_VERSION forces the ROCm runtime to treat the GPU as a
|
|
# specific GFX version when auto-detection fails or the GPU is newer than
|
|
# the ROCm release. app.py sets 10.3.0 (RDNA2) by default; override here
|
|
# for your GPU family:
|
|
# RDNA4 / RX 9000 series: 12.0.0
|
|
# (requires ROCM_VERSION=7.2)
|
|
# RDNA3 / RX 7000 series / Strix Halo: 11.0.0
|
|
# RDNA2 / RX 6000 series: 10.3.0
|
|
# RDNA1 / RX 5000 series: 10.1.0
|
|
# Vega / GCN5: 9.0.0
|
|
- HSA_OVERRIDE_GFX_VERSION=${HSA_OVERRIDE_GFX_VERSION:-}
|
|
|
|
# Tune the ROCm memory allocator
|
|
- PYTORCH_HIP_ALLOC_CONF=garbage_collection_threshold:0.8,max_split_size_mb:512
|