Files
esh-pfi-infrastructure/playbooks/deploy-vibevoice.yaml
T
vh ca16db73e0 playbooks: quiet down pip noise in TTS build logs
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.
2026-04-25 16:25:42 -07:00

98 lines
3.7 KiB
YAML

# Deploy VibeVoice 1.5B (long-form) to irv-ml1.
#
# Builds the image locally from groxaxo/VibeVoice-FastAPI1 via docker
# buildx git URL context. ~12 min cold build (CUDA 12.8 + torch 2.8 +
# flash-attn). First start downloads VibeVoice-1.5B (~7 GB) into the
# bind-mounted HF cache. Generous /healthz wait deadline accommodates
# both.
#
# Usage:
# scripts/elway irv-ml1 --playbook playbooks/deploy-vibevoice.yaml
#
# Idempotent — every step is creates-/when-gated; rerun is safe.
vars:
compose_dir: /opt/docker/compose/vibevoice
voices_dir: /worktank/vibevoice/voices
cache_dir: /worktank/vibevoice/cache
host_port: "8194"
steps:
# ── host-side dirs ──────────────────────────────────────────────────
- name: Ensure /worktank/vibevoice root exists (one-time, sudo)
shell: mkdir -p /worktank/vibevoice
sudo: true
creates: /worktank/vibevoice
- name: Chown /worktank/vibevoice to lkraven
shell: chown lkraven:lkraven /worktank/vibevoice
sudo: true
when: '[ "$(stat -c %U /worktank/vibevoice)" != lkraven ]'
- name: Ensure voices dir exists
shell: mkdir -p {{ voices_dir }}
creates: "{{ voices_dir }}"
- name: Ensure cache dir exists
shell: mkdir -p {{ cache_dir }}
creates: "{{ cache_dir }}"
- name: Ensure compose dir exists
shell: mkdir -p {{ compose_dir }}
creates: "{{ compose_dir }}"
# ── deploy compose files ────────────────────────────────────────────
- name: Upload compose.yaml
upload:
src: stacks/vibevoice/compose.yaml
dest: "{{ compose_dir }}/compose.yaml"
mode: "0644"
- name: Seed .env from template (only if absent)
upload:
src: stacks/vibevoice/.env.example
dest: "{{ compose_dir }}/.env"
mode: "0644"
when: "[ ! -f {{ compose_dir }}/.env ]"
# ── build + bring up ────────────────────────────────────────────────
- name: docker compose build (~12 min first time; cached after)
# --progress=plain stops the carriage-return TUI from littering the log
# with garbled redraws. The grep drops pip's Downloading / Collecting /
# Requirement / progress-bar lines (~25% of the log) while keeping
# buildkit step transitions, DONE/CACHED/ERROR markers, and any apt /
# build-stage messages worth seeing. 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 /health to respond (allow ~20 min for model download + warmup)
shell: |
for i in $(seq 1 240); 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: /v1/audio/voices returns valid JSON
shell: curl -sf http://localhost:{{ host_port }}/v1/audio/voices | grep -q '"voices"\|"voice"\|alloy\|Carter'
changed_when: "false"
- name: Container is running
shell: docker inspect vibevoice --format '{{.State.Status}}' | grep -q running
changed_when: "false"