Files
rocm-chatterbox-whisper/docker-compose.yml
scott 7a966c8532
Some checks failed
Build ROCm Image / build (push) Has been cancelled
Fix MIOPEN_FIND_ENFORCE: 3 -> 1 (DB_UPDATE)
Enforce=3 (SEARCH_DB_UPDATE) runs exhaustive kernel benchmarking on
every single GPU operation, making inference impossibly slow. Enforce=1
searches once, writes to cache, then reuses cached results on all
subsequent calls.

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
2026-04-05 12:29:54 -04:00

44 lines
1.3 KiB
YAML

services:
chatterbox-whisper:
image: git.sdgarren.com/scott/rocm-chatterbox-whisper:latest
build:
context: .
dockerfile: Dockerfile.rocm
restart: unless-stopped
ports:
- "${WYOMING_PORT:-10200}:10200"
devices:
- /dev/kfd
- /dev/dri
group_add:
- video
- render
ipc: host
shm_size: 8g
security_opt:
- seccomp=unconfined
volumes:
- ./config.yaml:/app/config.yaml
- ./voices:/app/voices
- ./reference_audio:/app/reference_audio
- hf_cache:/app/hf_cache
- miopen_cache:/app/miopen_cache
environment:
- HF_HUB_ENABLE_HF_TRANSFER=1
# MIOpen: search for best solver once and cache (1=DB_UPDATE).
# Never use 3 (SEARCH_DB_UPDATE) in production - it benchmarks on every call.
- MIOPEN_FIND_ENFORCE=1
# Persist MIOpen's kernel cache so it doesn't recompile on every start.
- MIOPEN_USER_DB_PATH=/app/miopen_cache
- MIOPEN_CUSTOM_CACHE_DIR=/app/miopen_cache
# HSA_OVERRIDE_GFX_VERSION is only needed for GPUs not natively supported
# by ROCm 7.2. Older cards may still need an override:
# 10.3.0 = RX 5000/6000 series
# 9.0.6 = Vega
# - HSA_OVERRIDE_GFX_VERSION=10.3.0
# - HF_TOKEN=your_token_here
volumes:
hf_cache:
miopen_cache: