mARTin
60db1b181f
Run Qwen3-TTS with CUDA graph acceleration on NVIDIA DGX Spark (ARM64 / SM 121 / CUDA 13) as an OpenAI-compatible TTS API server. - Dockerfile targeting nvidia/cuda:13.0.2-base-ubuntu24.04 with ARM64 cu130 PyTorch wheels - Patch for max-seq-len support to handle long reference audio without crashes - OpenWebUI + SillyTavern compatible API endpoints (/v1/models, /v1/audio/voices, /speakers) - Voice management: auto-generate voices.json from speaker reference audio files - Auto-transcription helper script for generating reference text from audio Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
21 lines
888 B
Diff
21 lines
888 B
Diff
diff --git a/examples/openai_server.py b/examples/openai_server.py
|
|
index 2199e14..d38a684 100644
|
|
--- a/examples/openai_server.py
|
|
+++ b/examples/openai_server.py
|
|
@@ -306,6 +306,7 @@ def _parse_args():
|
|
p.add_argument("--host", default="0.0.0.0", help="Bind host (default: 0.0.0.0)")
|
|
p.add_argument("--port", type=int, default=8000, help="Bind port (default: 8000)")
|
|
p.add_argument("--device", default="cuda", help="Torch device (default: cuda)")
|
|
+ p.add_argument("--max-seq-len", type=int, default=4096, help="Max sequence length for CUDA graph static cache (default: 4096)")
|
|
return p.parse_args()
|
|
|
|
|
|
@@ -344,6 +345,7 @@ def main():
|
|
args.model,
|
|
device=args.device,
|
|
dtype=torch.bfloat16,
|
|
+ max_seq_len=args.max_seq_len,
|
|
)
|
|
SAMPLE_RATE = tts_model.sample_rate
|
|
logger.info("Model ready. Sample rate: %d Hz", SAMPLE_RATE)
|