feat: nginx-based data parallel for optimal ASR throughput

When --dp N is specified (N > 1), the launcher now starts N independent
vLLM processes behind an nginx reverse proxy instead of using vLLM's
built-in DP coordinator. This avoids the single-process HTTP bottleneck
when handling large base64 audio payloads, achieving near-linear scaling
(7.2x with 8 GPUs at 4096 concurrent requests).

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

docs/vibevoice-vllm-asr.md

@@ -47,7 +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 — vLLM automatically distributes incoming requests:
+Run 4 independent replicas on 4 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:
 
 ```bash
 docker run -d --gpus '"device=0,1,2,3"' --name vibevoice-vllm \
@@ -62,6 +64,21 @@ docker run -d --gpus '"device=0,1,2,3"' --name vibevoice-vllm \
   -c "python3 /app/vllm_plugin/scripts/start_server.py --dp 4"
 ```
 
+Run on all 8 GPUs:
+
+```bash
+docker run -d --gpus all --name vibevoice-vllm \
+  --ipc=host \
+  -p 8000:8000 \
+  -e VIBEVOICE_FFMPEG_MAX_CONCURRENCY=64 \
+  -e PYTORCH_ALLOC_CONF=expandable_segments:True \
+  -v $(pwd):/app \
+  -w /app \
+  --entrypoint bash \
+  vllm/vllm-openai:v0.14.1 \
+  -c "python3 /app/vllm_plugin/scripts/start_server.py --dp 8"
+```
+
 ### Tensor Parallel
 
 Split a single model across 2 GPUs (useful if GPU memory is limited):