vh
131d746c92
Three fixes from the second-wave deploy attempts:
* voxtral: vllm/vllm-omni doesn't publish a `latest` tag — pull
failed with "manifest unknown". Pinned VOXTRAL_VLLM_TAG to v0.18.0
(released 2026-03-29, the day after the Voxtral 4B TTS release —
first cut with Voxtral support).
* kyutai-tts: NillPointer wrapper exposes ONLY /health (root) and
POST /v1/audio/speech. No /v1/models, no /v1/audio/voices —
those return 404. Verified by /openapi.json against the live
container. Compose healthcheck + playbook wait + verify steps
all repointed at the actual paths. POST /v1/audio/speech is now
smoke-tested with a RIFF WAV assertion (same pattern as fish-s2).
* fish-s2: added FISH_S2_MODEL env var so the model variant is
swappable via .env without rebuilding. Both s2-pro (default) and
s1-mini are pre-pulled into the bind-mount; LLAMA_CHECKPOINT_PATH
+ DECODER_CHECKPOINT_PATH now use ${FISH_S2_MODEL:-s2-pro}.
s1-mini was originally gated on fishaudio's HF org (401), but
niobures/OpenAudio-S1 mirrors the same files openly — pulled
from there via a one-shot snapshot_download.
107 lines
3.9 KiB
YAML
107 lines
3.9 KiB
YAML
# Deploy Kyutai TTS (1.6B EN/FR streaming, 220 ms claimed latency) to
|
|
# irv-ml1.
|
|
#
|
|
# Builds the image locally from NillPointer/Kyutai-TTS-Server via
|
|
# docker buildx git URL context. ~5-8 min cold build (CUDA + torch +
|
|
# moshi + Kyutai's Mimi codec deps). First start downloads
|
|
# kyutai/tts-1.6b-en_fr (~3-6 GB) into the bind-mounted HF cache.
|
|
#
|
|
# Usage:
|
|
# scripts/elway irv-ml1 --playbook playbooks/deploy-kyutai-tts.yaml
|
|
#
|
|
# Note: Kyutai's official deploy is Rust + websockets only. This stack
|
|
# uses the NillPointer community wrapper to bridge to OpenAI-compat
|
|
# HTTP — adds Python overhead on the request path, so measured TTFB
|
|
# will be higher than the bare-Rust 220 ms claim. See README.
|
|
#
|
|
# Idempotent — every step is creates-/when-gated; rerun is safe.
|
|
|
|
vars:
|
|
compose_dir: /opt/docker/compose/kyutai-tts
|
|
voices_dir: /worktank/kyutai-tts/voices
|
|
cache_dir: /worktank/kyutai-tts/hf_cache
|
|
host_port: "8198"
|
|
|
|
steps:
|
|
# ── host-side dirs ──────────────────────────────────────────────────
|
|
|
|
- name: Ensure /worktank/kyutai-tts root exists (one-time, sudo)
|
|
shell: mkdir -p /worktank/kyutai-tts
|
|
sudo: true
|
|
creates: /worktank/kyutai-tts
|
|
|
|
- name: Chown /worktank/kyutai-tts to lkraven
|
|
shell: chown -R lkraven:lkraven /worktank/kyutai-tts
|
|
sudo: true
|
|
when: "[ \"$(stat -c %U /worktank/kyutai-tts)\" != \"lkraven\" ]"
|
|
|
|
- name: Ensure voices dir exists
|
|
shell: mkdir -p {{ voices_dir }}
|
|
creates: "{{ voices_dir }}"
|
|
|
|
- name: Ensure HF 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 + env ────────────────────────────────────────────
|
|
|
|
- name: Upload compose.yaml
|
|
upload:
|
|
src: stacks/kyutai-tts/compose.yaml
|
|
dest: "{{ compose_dir }}/compose.yaml"
|
|
mode: "0644"
|
|
|
|
- name: Seed .env from template (only if absent)
|
|
upload:
|
|
src: stacks/kyutai-tts/.env.example
|
|
dest: "{{ compose_dir }}/.env"
|
|
mode: "0644"
|
|
when: "[ ! -f {{ compose_dir }}/.env ]"
|
|
|
|
# ── build + bring up ────────────────────────────────────────────────
|
|
|
|
- name: docker compose build (~5-8 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 download + warmup)
|
|
shell: |
|
|
for i in $(seq 1 120); do
|
|
curl -sf -o /dev/null --max-time 3 http://localhost:{{ host_port }}/health && exit 0
|
|
sleep 5
|
|
done
|
|
exit 1
|
|
changed_when: "false"
|
|
|
|
verify:
|
|
- name: /health returns 200
|
|
shell: curl -sf -o /dev/null http://localhost:{{ host_port }}/health
|
|
changed_when: "false"
|
|
|
|
- name: /v1/audio/speech returns a real WAV (POST with text body)
|
|
# NillPointer wrapper exposes ONLY /health and POST /v1/audio/speech
|
|
# (no /v1/models, no /v1/audio/voices). Smoke by POSTing and
|
|
# asserting a RIFF WAV comes back.
|
|
shell: |
|
|
out=$(mktemp --suffix=.wav)
|
|
curl -sf -X POST http://localhost:{{ host_port }}/v1/audio/speech \
|
|
-H 'Content-Type: application/json' \
|
|
-d '{"model":"tts-1.6b-en_fr","input":"Verify."}' \
|
|
-o "$out" --max-time 30
|
|
file -b "$out" | grep -q '^RIFF.*WAVE'
|
|
rm -f "$out"
|
|
changed_when: "false"
|
|
|
|
- name: Container is running
|
|
shell: docker inspect kyutai-tts --format '{{.State.Status}}' | grep -q running
|
|
changed_when: "false"
|