Skip to content

Open-Source Frontier Voice AI

Python

feat: set nginx workers to 2×dp for optimal HTTP throughput

Jianwei Yucd945395d4d6
diff --git a/docs/vibevoice-vllm-asr.md b/docs/vibevoice-vllm-asr.md
index bde87c8..9ed738b 100644
--- a/docs/vibevoice-vllm-asr.md
+++ b/docs/vibevoice-vllm-asr.md
@@ -47,9 +47,9 @@ The launcher supports two types of GPU parallelism via `--tp` and `--dp` flags:
### Data Parallel (Recommended for scaling throughput)
-Run 4 independent replicas on 4 GPUs with automatic load balancing behind a single port.
+Run N independent replicas on N GPUs with automatic load balancing behind a single port.
When `--dp N` is specified (N > 1), the launcher automatically starts N independent vLLM
-processes behind an nginx reverse proxy for optimal throughput:
+processes behind an nginx reverse proxy (2×N workers) for optimal throughput:
```bash
docker run -d --gpus '"device=0,1,2,3"' --name vibevoice-vllm \
diff --git a/vllm_plugin/scripts/start_server.py b/vllm_plugin/scripts/start_server.py
index 19e70d0..6c50377 100644
--- a/vllm_plugin/scripts/start_server.py
+++ b/vllm_plugin/scripts/start_server.py
@@ -146,11 +146,18 @@ def _install_nginx() -> None:
)
-def _write_nginx_config(frontend_port: int, backend_ports: list[int]) -> str:
- """Write nginx config for round-robin load balancing."""
+def _write_nginx_config(frontend_port: int, backend_ports: list[int],
+ num_workers: int = 0) -> str:
+ """Write nginx config for round-robin load balancing.
+
+ Args:
+ num_workers: Number of nginx worker processes. 0 = auto (2 × num backends).
+ """
+ if num_workers <= 0:
+ num_workers = len(backend_ports) * 2
backends = "\n".join(f" server 127.0.0.1:{p};" for p in backend_ports)
config = textwrap.dedent(f"""\
- worker_processes auto;
+ worker_processes {num_workers};
worker_rlimit_nofile 65536;
error_log /dev/stderr warn;
pid /tmp/nginx.pid;