mARTin-B78
1fc2f9c909
The upstream openai_server.py gained --max-seq-len after v5 was built. Add it to the patch so every build gets explicit sequence length control. Also add max_seq_len=args.max_seq_len to FasterQwen3TTS.from_pretrained() so the argument is actually used. Remove || true from git apply so patch failures fail the build instead of silently producing a broken image. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
42 lines
2.1 KiB
Diff
42 lines
2.1 KiB
Diff
diff --git a/examples/openai_server.py b/examples/openai_server.py
|
|
index 61047ea..2b0c8bb 100644
|
|
--- a/examples/openai_server.py
|
|
+++ b/examples/openai_server.py
|
|
@@ -187,7 +187,10 @@ async def _stream_chunks(voice_cfg: dict, text: str) -> AsyncGenerator[bytes, No
|
|
ref_text=voice_cfg.get("ref_text", ""),
|
|
chunk_size=voice_cfg.get("chunk_size", 12),
|
|
instruct=voice_cfg.get("instruct"),
|
|
- non_streaming_mode=False,
|
|
+ non_streaming_mode=True,
|
|
+ temperature=voice_cfg.get("temperature", 0.8),
|
|
+ top_k=voice_cfg.get("top_k", 50),
|
|
+ top_p=voice_cfg.get("top_p", 0.9),
|
|
):
|
|
q.put(chunk)
|
|
except Exception as exc:
|
|
@@ -252,6 +255,10 @@ async def create_speech(req: SpeechRequest):
|
|
ref_audio=voice_cfg["ref_audio"],
|
|
ref_text=voice_cfg.get("ref_text", ""),
|
|
instruct=voice_cfg.get("instruct"),
|
|
+ non_streaming_mode=True,
|
|
+ temperature=voice_cfg.get("temperature", 0.8),
|
|
+ top_k=voice_cfg.get("top_k", 50),
|
|
+ top_p=voice_cfg.get("top_p", 0.9),
|
|
)
|
|
|
|
audio_arrays, sr = await loop.run_in_executor(None, _generate)
|
|
@@ -306,4 +309,5 @@ 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()
|
|
@@ -341,6 +349,7 @@ def main():
|
|
logger.info("Loading model %s on %s …", args.model, args.device)
|
|
tts_model = FasterQwen3TTS.from_pretrained(
|
|
args.model,
|
|
device=args.device,
|
|
dtype=torch.bfloat16,
|
|
+ max_seq_len=args.max_seq_len,
|
|
)
|