qwen3-tts: wire optimized backend to /app/config.yaml so model registry actually loads

The wrapper's `optimized` backend (torch.compile + CUDA graphs +
real-time streaming) reads its model registry from a YAML config:
default path is ~/qwen3-tts/config.yaml inside the container, which
doesn't exist. Without TTS_CONFIG set, the backend boots with an
empty registry and every synthesis request fails with
"Unknown model key: '<name>'. Available: []".

The repo ships /app/config.yaml with all 4 model variants defined.
Pointing TTS_CONFIG at it lets the optimized backend load cleanly.

This is a prerequisite for benching the optimized backend properly
— it's the path to the upstream's claimed 97 ms streaming TTFB. The
default `official` backend uses naive HF transformers autoregressive
generation that pegged GPU at only 27% utilization and gave us 8-12 s
TTFB on bench (no recompile theory needed — same phrase repeated 4x
plateaued at 8.5 s, ruling out shape-specific recompilation).

stacks/qwen3-tts/compose.yaml

@@ -52,6 +52,13 @@ services:
       - PORT=8880
       - TTS_BACKEND=${QWEN3_TTS_BACKEND:-official}
       - TTS_MODEL_NAME=${QWEN3_TTS_MODEL:-Qwen/Qwen3-TTS-12Hz-1.7B}
+      # Only used when TTS_BACKEND=optimized — points the optimized backend
+      # at the upstream config.yaml (which defines the model registry +
+      # default model). Without this, the optimized backend looks at
+      # ~/qwen3-tts/config.yaml inside the container, which doesn't exist
+      # at runtime, leaving the model registry empty and synthesis fails
+      # with "Unknown model key".
+      - TTS_CONFIG=/app/config.yaml
       - TTS_WARMUP_ON_START=${QWEN3_TTS_WARMUP:-true}
       - TTS_MAX_CONCURRENT=${QWEN3_TTS_MAX_CONCURRENT:-1}
       - ENABLE_VOICE_STUDIO=${QWEN3_TTS_VOICE_STUDIO:-true}