vh
ca16db73e0
Profiling the index-tts deploy log (2057 lines) showed ~25% was just
pip's per-package Downloading / Collecting / Requirement-already /
progress-bar spam — useless for ops, hard to scan when something
actually breaks.
Three changes across the four TTS deploy playbooks:
1. Pulls (Kokoro): add --quiet. 6.5 GB pull no longer floods the log
with per-layer progress redraws. Final "X Pulled" still prints.
2. Builds (VibeVoice, Chatterbox, IndexTTS-2): add --progress=plain
to stop the BuildKit TUI from littering the captured log with
carriage-return overdraws, then pipe through a grep filter that
drops pip's noisy lines but keeps:
- buildkit step transitions (#NN [stage])
- DONE / CACHED / ERROR markers
- apt + build-stage messages
set -o pipefail keeps a real build failure from being swallowed
by the grep's exit code.
Net effect: ~25% smaller logs, much more scannable; full visibility
into step progress and errors preserved.
126 lines
4.4 KiB
YAML
126 lines
4.4 KiB
YAML
# Deploy IndexTTS-2 (https://github.com/index-tts/index-tts) to irv-ml1
|
|
# behind our own FastAPI wrapper (stacks/index-tts/app.py).
|
|
#
|
|
# Builds the image locally from the Dockerfile in stacks/index-tts/
|
|
# (which clones the upstream IndexTTS-2 repo at a pinned SHA inside
|
|
# the build), stages app.py + entrypoint.sh + compose + .env under
|
|
# /opt/docker/compose/index-tts/, brings it up, waits for /healthz,
|
|
# and verifies the API surface.
|
|
#
|
|
# First run is slow: ~5-10 min for the docker build (CUDA torch + the
|
|
# IndexTTS pinned-deps tail) plus ~5-7 GB model download from HF on
|
|
# first container start (entrypoint.sh handles that). The healthz wait
|
|
# below allows up to 15 min total.
|
|
#
|
|
# Usage:
|
|
# scripts/elway irv-ml1 --playbook playbooks/deploy-index-tts.yaml
|
|
#
|
|
# Idempotent — every step is creates-/when-gated; rerun is safe.
|
|
|
|
vars:
|
|
compose_dir: /opt/docker/compose/index-tts
|
|
cache_dir: /worktank/index-tts/cache
|
|
voices_dir: /worktank/index-tts/voices
|
|
emotions_dir: /worktank/index-tts/emotions
|
|
host_port: "8192"
|
|
|
|
steps:
|
|
# ── host-side dirs ──────────────────────────────────────────────────
|
|
|
|
- name: Ensure /worktank/index-tts root exists (one-time, sudo)
|
|
shell: mkdir -p /worktank/index-tts
|
|
sudo: true
|
|
creates: /worktank/index-tts
|
|
|
|
- name: Chown /worktank/index-tts to lkraven
|
|
shell: chown lkraven:lkraven /worktank/index-tts
|
|
sudo: true
|
|
when: '[ "$(stat -c %U /worktank/index-tts)" != lkraven ]'
|
|
|
|
- name: Ensure cache dir exists
|
|
shell: mkdir -p {{ cache_dir }}
|
|
creates: "{{ cache_dir }}"
|
|
|
|
- name: Ensure voices dir exists
|
|
shell: mkdir -p {{ voices_dir }}
|
|
creates: "{{ voices_dir }}"
|
|
|
|
- name: Ensure emotions dir exists
|
|
shell: mkdir -p {{ emotions_dir }}
|
|
creates: "{{ emotions_dir }}"
|
|
|
|
- name: Ensure compose dir exists
|
|
shell: mkdir -p {{ compose_dir }}
|
|
creates: "{{ compose_dir }}"
|
|
|
|
# ── deploy build context (compose, env, dockerfile, app, entrypoint) ──
|
|
|
|
- name: Upload compose.yaml
|
|
upload:
|
|
src: stacks/index-tts/compose.yaml
|
|
dest: "{{ compose_dir }}/compose.yaml"
|
|
mode: "0644"
|
|
|
|
- name: Upload Dockerfile
|
|
upload:
|
|
src: stacks/index-tts/Dockerfile
|
|
dest: "{{ compose_dir }}/Dockerfile"
|
|
mode: "0644"
|
|
|
|
- name: Upload app.py
|
|
upload:
|
|
src: stacks/index-tts/app.py
|
|
dest: "{{ compose_dir }}/app.py"
|
|
mode: "0644"
|
|
|
|
- name: Upload entrypoint.sh
|
|
upload:
|
|
src: stacks/index-tts/entrypoint.sh
|
|
dest: "{{ compose_dir }}/entrypoint.sh"
|
|
mode: "0755"
|
|
|
|
- name: Seed .env from template (only if absent)
|
|
upload:
|
|
src: stacks/index-tts/.env.example
|
|
dest: "{{ compose_dir }}/.env"
|
|
mode: "0644"
|
|
when: "[ ! -f {{ compose_dir }}/.env ]"
|
|
|
|
# ── build + bring up ────────────────────────────────────────────────
|
|
|
|
- name: docker compose build (~5-10 min first time; cached after)
|
|
# --progress=plain stops carriage-return TUI from littering the log.
|
|
# The grep drops pip's per-package Downloading/Collecting/Requirement
|
|
# noise (~25% of the log on first build) while keeping buildkit step
|
|
# transitions and DONE/CACHED/ERROR markers. set -o pipefail so a
|
|
# build failure isn't swallowed by the grep return code.
|
|
shell: |
|
|
set -o pipefail
|
|
cd {{ compose_dir }} && docker compose build --progress=plain 2>&1 \
|
|
| grep -vE '^#[0-9]+ [0-9.]+ (Downloading|Collecting|Requirement|Using cached|Installing collected|Successfully (installed|built)|Saved /|━|Resolved|Prepared|Built)'
|
|
|
|
- name: docker compose up -d
|
|
shell: cd {{ compose_dir }} && docker compose up -d
|
|
|
|
- name: Wait for /healthz to respond (allow ~15 min for model download)
|
|
shell: |
|
|
for i in $(seq 1 180); do
|
|
curl -sf -o /dev/null --max-time 3 http://localhost:{{ host_port }}/healthz && exit 0
|
|
sleep 5
|
|
done
|
|
exit 1
|
|
changed_when: "false"
|
|
|
|
verify:
|
|
- name: /healthz returns 200
|
|
shell: curl -sf -o /dev/null http://localhost:{{ host_port }}/healthz
|
|
changed_when: "false"
|
|
|
|
- name: /v1/voices returns a JSON object with 'voices' and 'emotions' keys
|
|
shell: curl -sf http://localhost:{{ host_port }}/v1/voices | grep -q '"voices"'
|
|
changed_when: "false"
|
|
|
|
- name: Container is running
|
|
shell: docker inspect index-tts --format '{{.State.Status}}' | grep -q running
|
|
changed_when: "false"
|