vh
d2ed7671d7
Three upstream gaps surfaced once /generate was actually exercised:
1. infer-api.py builds an 18-arg positional tuple but the pipeline
expects 24 — first missing arg is `format`, so audio_duration
shifts into format's slot and the pipeline calls len() on an
int. Ship a patched copy of infer-api.py and COPY over upstream's
in the Dockerfile. Also handle empty lora_name_or_path -> "none"
(empty string trips HF Hub's repo-id validator).
2. torchcodec + ffmpeg are required by the WAV save path but neither
is in upstream requirements.txt. Without them every /generate
runs to completion and then 500s at write-time.
3. ACE-Step caches checkpoints at /root/.cache/ace-step/checkpoints
(HARDCODED, not honored by HF_HOME). Mount our persistent dir
there so the ~7 GB model survives container recreates.
Bench on A6000 (cached model, lo-fi hip hop, 60-step euler/apg):
10s @ 27 steps -> 9.4s (0.94x)
30s @ 60 steps -> 11.2s (0.37x, ~2.7x realtime)
60s @ 60 steps -> 14.8s (0.24x, ~4x realtime)
ace-step
ACE-Step 1.5 — Apache 2.0 open-source music generation foundation model. Hybrid diffusion + LLM. Generates lyric-aware multi-minute songs (vocals + instrumentation).
| host | irv-ml1 |
| port | 8210 |
| GPU | A6000 (device_ids: ["1"]) |
| VRAM | ~10-12 GB during inference |
| upstream | https://github.com/ace-step/ACE-Step |
| license | Apache 2.0 |
API surface
infer-api.py (FastAPI) exposes:
GET /health— liveness, returns 200 once the process is up (model is lazy-loaded on first /generate).POST /generate— body:ACEStepInputPydantic model with ~27 params (prompt, lyrics, audio_duration, guidance_scale, etc.). Returns{status, output_path, message}.
The container does NOT expose the Gradio UI — we override the upstream
default python3 acestep/gui.py with python3 infer-api.py. If you
want the Gradio UI for ad-hoc experimentation, run a one-off:
ssh irv-ml1 'docker exec -it ace-step python3 acestep/gui.py --server_name 0.0.0.0 --port 7865'
…and port-forward 7865 to your laptop.
Deploy
scripts/elway irv-ml1 --playbook playbooks/deploy-ace-step.yaml
Idempotent. Cold build is ~10-15 min (CUDA + torch + transformers +
spacy + audio deps). First /generate triggers the model download
(~5-10 GB) and warmup (~30-60 s).
Tunables
See .env.example — copy to .env on the host (lives at
/opt/docker/compose/ace-step/.env, gitignored). Common knobs:
ACE_STEP_SHA— pin upstream commitACE_STEP_GPU_DEVICES— GPU indexACE_STEP_*_DIR— bind-mount paths under/worktank/ace-step/