48013a4a92
New `infra/stacks/tts/` deploys devnen/Chatterbox-TTS-Server (OpenAI-compatible /v1/audio/speech) as ClusterIP `chatterbox-tts.tts.svc:8000` (server listens on 8004; Service remaps), requesting ONE T4 time-slice. Mirrors stacks/llama-cpp/. Option A off-peak control (no VRAM isolation on the time-sliced T4 — see post-mortem 2026-06-02): Deployment sits at replicas=0; three Europe/London CronJobs own the replica count — `chatterbox-window-up` scales to 1 at 02:00 ONLY IF a free-VRAM preflight passes (sum gpu_pod_memory_used_bytes from gpu-pod-exporter; free = 16GiB - used >= floor), `chatterbox-vram-guard` yields the card mid-window if a resident wakes, `chatterbox-window-down` scales to 0 at 06:00. tripit's bake is best-effort + cached-forever (ADR-0002/0004) so a skipped/aborted window backfills next time. SA+Role+RoleBinding grant the CronJobs deployments/scale (nextcloud-watchdog pattern). Polite-tenant hardening: kyverno `inject-gpu-workload-priority` now excludes the `tts` namespace (new `gpu_priority_excluded_namespaces` local) so Chatterbox keeps tier-2-gpu priority (600k) and is always evicted first under GPU pressure — never immich-ml/frigate/llama-swap. The LimitRange-fallback policy still uses the base exclude list (tts untouched there). tripit: add TTS_MODE=openai_compatible, TTS_BASE_URL, TTS_MODEL=chatterbox to local.app_env (no token — ClusterIP only). No tripit code change. Image build is documented in stacks/tts/README.md (devnen cu128 target -> forgejo.viktorbarzin.me/viktor/chatterbox-tts) — build is impractical inline (large CUDA image + needs the upstream repo). NOT APPLIED — review branch only. Free-VRAM floor (var.vram_free_floor_bytes, default 6GiB) must be set from the measured chatterbox-multilingual T4 peak during the first bake. Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
149 lines
7 KiB
Markdown
149 lines
7 KiB
Markdown
# tts — Chatterbox TTS (tripit narration)
|
||
|
||
In-cluster text-to-speech for tripit's "Tour guide". Runs the
|
||
[devnen/Chatterbox-TTS-Server](https://github.com/devnen/Chatterbox-TTS-Server)
|
||
(Resemble AI Chatterbox under an OpenAI-compatible HTTP server) as a single
|
||
Deployment + ClusterIP Service `chatterbox-tts.tts.svc.cluster.local:8000`,
|
||
requesting **one time-slice** of the shared Tesla T4 (`nvidia.com/gpu: 1`).
|
||
|
||
Full design + rationale (Option-A off-peak control, OOM analysis, ADR links):
|
||
`docs/plans/2026-06-08-chatterbox-tts-infra.md` (in the tripit-tour-guide repo)
|
||
and `infra/docs/post-mortems/2026-06-02-immich-ml-ttl-gpu-oom-recruiter.md`.
|
||
|
||
> This stack mirrors `infra/stacks/llama-cpp/`. The scaffolding files
|
||
> (`backend.tf`, `providers.tf`, `cloudflare_provider.tf`, `tiers.tf`,
|
||
> `.terraform.lock.hcl`) are **generated by Terragrunt** on `init` and are
|
||
> git-ignored — only `main.tf`, `terragrunt.hcl` and this README are tracked.
|
||
|
||
---
|
||
|
||
## What this stack creates
|
||
|
||
- `kubernetes_namespace.tts` — tier `2-gpu`, keel-enrolled, istio off.
|
||
- `module.nfs_models` — RWX NFS-SSD PVC at `/srv/nfs-ssd/chatterbox`, mounted at
|
||
`/data` (predefined voices, narrator reference WAVs, **and** the HuggingFace
|
||
model cache via `HF_HOME=/data/hf_cache`, so weights download once and persist
|
||
across the per-window pod recreation).
|
||
- `kubernetes_config_map.chatterbox_config` — `config.yaml`: `server.port=8004`,
|
||
`model.repo_id=chatterbox-multilingual`, `tts_engine.device=cuda`, voices /
|
||
reference paths under `/data`.
|
||
- `kubernetes_deployment.chatterbox` — **starts at `replicas=0`**; the off-peak
|
||
CronJobs own the replica count at runtime. `TTS_BF16=off` (T4 = Turing, no
|
||
bf16). `priority_class_name=tier-2-gpu` (the polite-tenant demotion).
|
||
- `kubernetes_service.chatterbox` — ClusterIP, **`port 8000 → targetPort 8004`**
|
||
so tripit's default `TTS_BASE_URL` works unchanged. Prometheus scrape
|
||
annotations.
|
||
- **Off-peak control** (SA + Role + RoleBinding + 3 CronJobs): see below.
|
||
|
||
## Off-peak control (Option A — window + free-VRAM gate)
|
||
|
||
The T4 is time-sliced with **zero VRAM isolation** (post-mortem 2026-06-02), so
|
||
`nvidia.com/gpu: 1` buys a scheduling turn, NOT memory. Chatterbox must only
|
||
allocate VRAM when the card is actually free. Implemented as three CronJobs
|
||
(all `Europe/London`), each a `bitnami/kubectl` pod using the namespace SA:
|
||
|
||
| CronJob | Schedule (default) | Action |
|
||
|---|---|---|
|
||
| `chatterbox-window-up` | `0 2 * * *` | **Preflight**: scrape `gpu_pod_memory_used_bytes` from `gpu-pod-exporter.nvidia.svc:80/metrics`, compute `free = 16 GiB − Σused`; scale to **1 only if** `free ≥ vram_free_floor_bytes`. |
|
||
| `chatterbox-vram-guard` | `*/5 2-5 * * *` | **Guard**: every 5 min in-window, scale to **0** if `free < floor` (a resident woke; yield the card mid-bake). |
|
||
| `chatterbox-window-down` | `0 6 * * *` | **Window end**: scale to **0** unconditionally. |
|
||
|
||
`tripit`'s bake is best-effort + cached-forever (ADR-0002/0004) — a skipped or
|
||
aborted window simply backfills on the next one. No latency SLA.
|
||
|
||
### The free-VRAM floor — YOU MUST MEASURE THIS
|
||
|
||
`var.vram_free_floor_bytes` defaults to **6 GiB** (a conservative guess:
|
||
~4 GiB assumed multilingual FP16 peak + ~2 GiB headroom for the
|
||
read→`cudaMalloc` race). **The real T4 peak of `chatterbox-multilingual` is not
|
||
published upstream.** Capture it during the first bake:
|
||
|
||
```bash
|
||
# while a real synth is running on the freed T4:
|
||
kubectl -n monitoring exec deploy/prometheus -- \
|
||
promtool query instant http://localhost:9090 \
|
||
'sum(gpu_pod_memory_used_bytes{namespace="tts"})'
|
||
# or read the gauge straight from the exporter:
|
||
kubectl -n nvidia exec ds/gpu-pod-exporter -- \
|
||
sh -c 'curl -s localhost:9401/metrics | grep "namespace=\"tts\""'
|
||
```
|
||
|
||
Then set the floor to `measured_peak + ~2 GiB` (pass `-var` or add to the stack
|
||
tfvars). If the peak is too high to coexist even off-peak, switch
|
||
`model.repo_id` in `main.tf` to `chatterbox` (English, lighter) or
|
||
`chatterbox-turbo`, or escalate to Option B (scale `immich-machine-learning` to
|
||
0 for the window).
|
||
|
||
---
|
||
|
||
## Build + push the image (do this BEFORE the first apply)
|
||
|
||
`devnen/Chatterbox-TTS-Server` ships **no published image** — build from the
|
||
repo's **cu128** target (matches the cluster's pinned 570.195.03 / CUDA 12.8
|
||
driver) and push to the private Forgejo registry. The devvm docker is pre-authed
|
||
to `forgejo.viktorbarzin.me`. Run on the devvm (large CUDA image — needs disk +
|
||
bandwidth):
|
||
|
||
```bash
|
||
# 1. Clone the upstream server repo (outside the monorepo).
|
||
git clone https://github.com/devnen/Chatterbox-TTS-Server /tmp/chatterbox-tts-server
|
||
cd /tmp/chatterbox-tts-server
|
||
|
||
# 2. Build the cu128 variant (Dockerfile.cu128 — PyTorch 2.9.0+cu128, the target
|
||
# the repo's docker-compose-cu128.yml uses) for linux/amd64.
|
||
SHA="$(git rev-parse --short=8 HEAD)"
|
||
docker build \
|
||
--platform linux/amd64 \
|
||
--build-arg RUNTIME=nvidia \
|
||
-f Dockerfile.cu128 \
|
||
-t forgejo.viktorbarzin.me/viktor/chatterbox-tts:latest \
|
||
-t "forgejo.viktorbarzin.me/viktor/chatterbox-tts:${SHA}" \
|
||
.
|
||
|
||
# 3. Push both tags. (If docker isn't authed: log in with the viktor push PAT
|
||
# from Vault — `vault kv get -field=forgejo_push_token secret/ci/global` —
|
||
# `docker login forgejo.viktorbarzin.me -u viktor`.)
|
||
docker push forgejo.viktorbarzin.me/viktor/chatterbox-tts:latest
|
||
docker push "forgejo.viktorbarzin.me/viktor/chatterbox-tts:${SHA}"
|
||
```
|
||
|
||
> If `Dockerfile.cu128` is not a clean `docker build` target (e.g. it relies on
|
||
> build args defined only in `docker-compose-cu128.yml`), lift those args onto
|
||
> the `docker build` line or `docker compose -f docker-compose-cu128.yml build`
|
||
> then `docker tag` the resulting `chatterbox-tts-server:cu128` image to the
|
||
> Forgejo ref above before pushing.
|
||
|
||
---
|
||
|
||
## Apply (admin-gated — run in order)
|
||
|
||
```bash
|
||
vault login -method=oidc
|
||
~/code/scripts/presence claim node:k8s-node1 --purpose "chatterbox-tts first apply (GPU)"
|
||
~/code/scripts/presence claim stack:tts --purpose "chatterbox-tts stack apply"
|
||
|
||
# 1. The polite-tenant hardening (exclude tts from gpu-workload priority).
|
||
~/code/scripts/tg plan --stack kyverno
|
||
~/code/scripts/tg apply --stack kyverno
|
||
|
||
# 2. This stack.
|
||
~/code/scripts/tg plan --stack tts
|
||
~/code/scripts/tg apply --stack tts # apply does NOT wake the GPU (replicas=0)
|
||
|
||
# 3. Flip tripit narration on.
|
||
~/code/scripts/tg plan --stack tripit
|
||
~/code/scripts/tg apply --stack tripit
|
||
```
|
||
|
||
See `docs/plans/2026-06-08-chatterbox-tts-infra.md` §5 for the full go-live
|
||
checklist (seed voices on NFS-SSD, smoke-test a synth, watch the neighbours).
|
||
|
||
## Rollback (instant, no data loss)
|
||
|
||
- **Narration off:** set `TTS_MODE=none` (or drop the three `TTS_*` lines) in
|
||
`stacks/tripit/main.tf` → `tg apply --stack tripit`. The bake makes no audio;
|
||
playback falls back to browser TTS. Cached `story_audio` rows are harmless.
|
||
- **Chatterbox off the GPU:** `kubectl -n tts scale deploy/chatterbox-tts
|
||
--replicas=0` (transient) and/or `tg destroy --stack tts`. Best-effort synth
|
||
means tripit bakes keep running audio-less — no error.
|
||
- Neither touches the resident GPU tenants (Option A never modifies them).
|