Files
vh d2ed7671d7 ace-step: patch upstream infer-api + missing runtime deps + cache mount
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)
2026-04-28 09:42:07 -07:00

90 lines
3.2 KiB
YAML

# Deploy ACE-Step 1.5 (Apache 2.0 music generation foundation model)
# to irv-ml1.
#
# Builds the image locally from ace-step/ACE-Step via docker buildx
# git URL context. ~10-15 min cold build (CUDA 12.6 runtime + torch +
# transformers + spacy + audio deps). First /generate triggers the
# model download (~5-10 GB) into the bind-mounted HF cache + warmup.
#
# Pre-req (user runs once):
# ssh -t irv-ml1 'sudo mkdir -p /worktank/ace-step/{checkpoints,outputs,logs,hf_cache} \
# /opt/docker/compose/ace-step && \
# sudo chown -R lkraven:lkraven /worktank/ace-step /opt/docker/compose/ace-step'
#
# Usage:
# scripts/elway irv-ml1 --playbook playbooks/deploy-ace-step.yaml
#
# Idempotent — every step is creates-/when-gated; rerun is safe.
vars:
compose_dir: /opt/docker/compose/ace-step
worktank_root: /worktank/ace-step
host_port: "8210"
steps:
# ── sanity checks (dirs were created by user-side sudo prep) ────────
- name: Verify /worktank/ace-step exists and is writable
shell: test -w {{ worktank_root }}
changed_when: "false"
- name: Verify compose dir exists and is writable
shell: test -w {{ compose_dir }}
changed_when: "false"
# ── deploy compose + env ────────────────────────────────────────────
- name: Upload compose.yaml
upload:
src: stacks/ace-step/compose.yaml
dest: "{{ compose_dir }}/compose.yaml"
mode: "0644"
- name: Upload Dockerfile (patched for cu126 torch resolution)
upload:
src: stacks/ace-step/Dockerfile
dest: "{{ compose_dir }}/Dockerfile"
mode: "0644"
- name: Upload patched infer-api.py (fixes upstream 18-arg tuple bug)
upload:
src: stacks/ace-step/infer-api.py
dest: "{{ compose_dir }}/infer-api.py"
mode: "0644"
- name: Seed .env from template (only if absent)
upload:
src: stacks/ace-step/.env.example
dest: "{{ compose_dir }}/.env"
mode: "0644"
when: "[ ! -f {{ compose_dir }}/.env ]"
# ── build + bring up ────────────────────────────────────────────────
- name: docker compose build (~10-15 min first time; cached after)
shell: |
set -o pipefail
cd {{ compose_dir }} && docker compose build 2>&1 \
| grep -vE '^#[0-9]+ |^ => |^=> |Collecting|Downloading|Requirement|Using cached|Installing collected|Successfully (installed|built)|━'
- name: docker compose up -d
shell: cd {{ compose_dir }} && docker compose up -d
- name: Wait for /health to respond (allow ~10 min for first model download + warmup)
shell: |
for i in $(seq 1 120); do
curl -sf -o /dev/null --max-time 3 http://localhost:{{ host_port }}/health && exit 0
sleep 5
done
exit 1
changed_when: "false"
verify:
- name: /health returns 200
shell: curl -sf -o /dev/null http://localhost:{{ host_port }}/health
changed_when: "false"
- name: Container is running
shell: docker inspect ace-step --format '{{.State.Status}}' | grep -q running
changed_when: "false"