tkrmagid/javis_bot
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases 20 Wiki Activity

fix: let melo-worker honour MELO_DEVICE from env (was hardcoded cpu)

Browse Source 
supervisord hardcoded MELO_DEVICE=cpu, overriding the compose MELO_DEVICE=cuda
so MeloTTS stayed on CPU even after the GPU torch swap. Interpolate the
container env instead.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
This commit is contained in:
javis-bot
2026-06-14 02:26:24 +09:00
parent 3d1e56f60f
commit b18217fcdd
1 changed files with 4 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

5
docker/supervisord.conf
View File

@@ -61,7 +61,10 @@ directory=/app
; HF_HUB_OFFLINE/TRANSFORMERS_OFFLINE force pure-cache reads: the pinned old
; transformers/huggingface_hub otherwise retry the network on every load and
; error out instead of falling back to the (complete) baked cache.
environment=MELO_LANGUAGE="KR",MELO_SPEED="1.5",MELO_DEVICE="cpu",MELO_WORKER_HOST="127.0.0.1",MELO_WORKER_PORT="8770",HF_HOME="/opt/melo-cache",HF_HUB_OFFLINE="1",TRANSFORMERS_OFFLINE="1"
; MELO_DEVICE inherits from the container env (compose sets it; default cuda)
; so the worker runs MeloTTS on the GPU. supervisord interpolates %(ENV_x)s
; from its own environment, which is the container's.
environment=MELO_LANGUAGE="KR",MELO_SPEED="1.5",MELO_DEVICE="%(ENV_MELO_DEVICE)s",MELO_WORKER_HOST="127.0.0.1",MELO_WORKER_PORT="8770",HF_HOME="/opt/melo-cache",HF_HUB_OFFLINE="1",TRANSFORMERS_OFFLINE="1"
priority=280
autorestart=true
stdout_logfile=/dev/stdout