[Refactor][Qwen3-TTS] Extract reusable prompt-embeds builder and make tts_pad_embed a persistent buffer (#3992)

Signed-off-by: Viacheslav Klimkov <vklimkov@nvidia.com>
Co-authored-by: Yueqian Lin <70319226+linyueqian@users.noreply.github.com>

tests/entrypoints/openai_api/test_qwen3_tts_speaker_embedding.py

@@ -28,7 +28,7 @@ MODEL_BASE = "Qwen/Qwen3-TTS-12Hz-0.6B-Base"
 MODEL_BASE_1_7B = "Qwen/Qwen3-TTS-12Hz-1.7B-Base"
 
 # A synthetic 1024-dim speaker embedding (all 0.1 — not a real voice, but
-# exercises the full code path through the talker's _build_prompt_embeds).
+# exercises the full code path through Qwen3TTSPromptEmbedsBuilder.build_prompt_embeds).
 DUMMY_EMBEDDING_1024 = [0.1] * 1024
 DUMMY_EMBEDDING_2048 = [0.1] * 2048