qwen3-tts/.env.example: document the optimized-backend crashloop trap

Investigation of the slow (8-12s) qwen3-tts TTFB found the upstream
wrapper has 5 backend options. The advertised path to fast TTFB is
TTS_BACKEND=optimized (torch.compile + CUDA graphs + real-time
streaming). It loads cleanly but crashes the container during its
hardcoded warmup phase — silent exit (ExitCode 0, no traceback,
no OOM kill), repeats every ~22s under restart policy.

TTS_WARMUP_ON_START=false suppresses the factory-level warmup but
the optimized backend has its own internal warmup that fires
regardless and triggers the crash.

Updated the .env.example block to enumerate all 5 backend options
with their actual current behavior so future-Claude doesn't re-walk
this path. official is staying as the default.

stacks/qwen3-tts/.env.example

@@ -20,9 +20,23 @@ QWEN3_TTS_PORT=8191
 QWEN3_TTS_BIND=0.0.0.0
 
 # ── runtime ──────────────────────────────────────────────────────────
-# Inference backend. `official` = default upstream; `optimized` =
+# Inference backend. Five options exposed by /app/api/backends/factory.py:
-# faster but slightly less robust; `vllm_omni` = vLLM-backed (needs
+#   official   — default. Naive HF transformers autoregressive loop.
-# more VRAM); `pytorch` = bare pytorch path.
+#                Reliable, but the GPU sits at ~27% utilization and
+#                TTFB on a sentence is 8-12s (no streaming endpoint
+#                tuning). 2026-04-27 bench confirmed.
+#   optimized  — torch.compile + CUDA graphs + real-time streaming.
+#                Should be the path to upstream's claimed 97 ms TTFB.
+#                CRASHES the container during its hardcoded warmup as
+#                of 2026-04-27 (silent ExitCode 0, no Traceback, repeats
+#                every ~22s under restart policy). TTS_WARMUP_ON_START=
+#                false doesn't help — the optimized backend's warmup is
+#                separate from the factory-level warmup. Don't use until
+#                upstream root-cause is identified or worked around.
+#   vllm_omni  — vLLM-Omni-backed. Faster but needs more VRAM and a
+#                vLLM dependency we haven't pulled. Untested.
+#   pytorch    — CPU-only fallback.
+#   openvino   — Intel CPU experimental.
 QWEN3_TTS_BACKEND=official
 
 # Model variant. Upstream publishes four checkpoints on HF: