Serialize A10G generation requests

Dockerfile

@@ -71,11 +71,11 @@ ENV HOME=/home/user \
     BACKEND_HOST=127.0.0.1 \
     BACKEND_PORT=8010 \
     AUDIO8_TTS_MEM_FRACTION_STATIC=0.60 \
-    AUDIO8_TTS_MAX_RUNNING_REQUESTS=2 \
+    AUDIO8_TTS_MAX_RUNNING_REQUESTS=1 \
     AUDIO8_TTS_MAX_TEXT_UNITS=150 \
     AUDIO8_TTS_MAX_RAW_TEXT_CHARS=1000 \
     AUDIO8_TTS_MAX_NEW_TOKENS=1024 \
-    UI_MAX_CONCURRENCY=2 \
+    UI_MAX_CONCURRENCY=1 \
     AUDIO8_TTS_DISABLE_CUDA_GRAPH=0 \
     AUDIO8_TTS_ENABLE_TORCH_COMPILE=1 \
     AUDIO8_TTS_VERIFY_FAST_KV=1 \

app.py

@@ -22,7 +22,7 @@ ALLOWED_AUDIO_SUFFIXES = {".wav", ".mp3", ".flac", ".m4a", ".ogg"}
 MAX_TEXT_UNITS = int(os.getenv("AUDIO8_TTS_MAX_TEXT_UNITS", "150"))
 MAX_RAW_TEXT_CHARS = int(os.getenv("AUDIO8_TTS_MAX_RAW_TEXT_CHARS", "1000"))
 MAX_NEW_TOKENS = int(os.getenv("AUDIO8_TTS_MAX_NEW_TOKENS", "1024"))
-GENERATION_LIMIT = asyncio.Semaphore(int(os.getenv("UI_MAX_CONCURRENCY", "2")))
+GENERATION_LIMIT = asyncio.Semaphore(int(os.getenv("UI_MAX_CONCURRENCY", "1")))
 
 ENGLISH_REFERENCE_TEXT = (
     "hello nice to meet you, what would you like to talk about todat"