docs: place V100 guide in deployment recipes

docs/en/model-deployment/index.md

@@ -43,6 +43,7 @@ flowchart LR
 | End-to-end self-test with no weights | [Mock](mock.md) |
 | First real lip-sync model | [Wav2Lip Local](wav2lip/local.md) |
 | Local STT/TTS + QuickTalk | [Local STT/TTS + QuickTalk](recipes/local-quicktalk-audio.md) |
+| V100 single-host FasterLivePortrait + FlashHead | [V100 + FasterLivePortrait + FlashHead](recipes/v100-fasterliveportrait-flashhead.md) |
 | Existing MuseTalk runtime | [MuseTalk with OmniRT](musetalk/omnirt.md) |
 | Local realtime adapter | [QuickTalk Local](quicktalk/local.md) |
 | Single-GPU realtime portrait with pasteback | [FasterLivePortrait](fasterliveportrait.md) |

docs/en/model-deployment/recipes/v100-fasterliveportrait-flashhead.md

@@ -0,0 +1,11 @@
+# V100 + FasterLivePortrait + FlashHead Deployment Recipe
+
+This V100 deployment recipe is currently maintained in Chinese:
+
+[Read the Chinese guide](https://datascale-ai.github.io/opentalking/model-deployment/recipes/v100-fasterliveportrait-flashhead/).
+
+It covers a single NVIDIA V100 32GB host running OpenTalking with:
+
+- FasterLivePortrait through OmniRT for real-person video-driven rendering.
+- FlashHead through a WebSocket bridge for image-conditioned generation.
+- V100-specific notes for FP16, TensorRT 8.6, disabled `torch.compile`, CUDA libraries, and WebRTC port exposure.

docs/zh/model-deployment/index.md

@@ -43,6 +43,7 @@ flowchart LR
 | 无权重端到端自测 | [Mock](mock.md) |
 | 第一个真实唇形模型 | [Wav2Lip Local](wav2lip/local.md) |
 | 本地 STT/TTS + QuickTalk | [本地 STT/TTS + QuickTalk](recipes/local-quicktalk-audio.md) |
+| V100 单机部署 FasterLivePortrait + FlashHead | [V100 + FasterLivePortrait + FlashHead](recipes/v100-fasterliveportrait-flashhead.md) |
 | 已有 MuseTalk runtime | [MuseTalk with OmniRT](musetalk/omnirt.md) |
 | 本地实时 adapter | [QuickTalk Local](quicktalk/local.md) |
 | 单卡实时头像贴回链路 | [FasterLivePortrait](fasterliveportrait.md) |

docs/zh/model-deployment/recipes/v100-fasterliveportrait-flashhead.md

@@ -1,9 +1,13 @@
-# V100 实时数字人部署完整指南
+# V100 + FasterLivePortrait + FlashHead 部署配方
 
 > 从零开始，在 NVIDIA V100 (32GB) 上部署实时对话数字人系统
 > 包含两套推理方案：FasterLivePortrait（真人驱动）+ FlashHead（AI生成）
 > 适用环境：Ubuntu 22.04 + NVIDIA Driver 580 + CUDA 12.x
 
+本页是一份面向 V100 单机的实战部署配方。通用模型说明请先阅读
+[FasterLivePortrait](../fasterliveportrait.md)、[FlashHead](../flashhead.md) 和
+[OmniRT 部署](../backends/omnirt.md)。
+
 ---
 
 ## 一、系统架构
@@ -240,7 +244,7 @@ cp libgrid_sample_3d_plugin.so \
 
 ```bash
 cd /opt/digital-human
-git clone https://github.com/anthropics/omnirt.git  # 或从内部获取
+git clone https://github.com/datascale-ai/omnirt.git
 cd omnirt
 
 source /opt/digital-human/omnirt/.venv310/bin/activate
@@ -510,7 +514,7 @@ python /opt/digital-human/flashhead_server.py
 
 ```bash
 cd /opt/digital-human
-git clone https://github.com/anthropics/opentalking.git
+git clone https://github.com/datascale-ai/opentalking.git
 cd opentalking
 ```
 

mkdocs.yml

@@ -132,6 +132,7 @@ plugins:
             Recipes: 部署配方
             Wav2Lip Local: Wav2Lip Local
             Local Audio + QuickTalk: 本地语音 + QuickTalk
+            V100 + FasterLivePortrait + FlashHead: V100 + FasterLivePortrait + FlashHead
             Avatar Assets: Avatar 资产
             Talking-Head Models: Talking-head 模型
             Talking-Head Model Deployment: 数字人模型部署
@@ -266,6 +267,7 @@ nav:
               - FasterLivePortrait: model-deployment/fasterliveportrait.md
           - Recipes:
               - Local Audio + QuickTalk: model-deployment/recipes/local-quicktalk-audio.md
+              - V100 + FasterLivePortrait + FlashHead: model-deployment/recipes/v100-fasterliveportrait-flashhead.md
           - LLM and STT: model-deployment/llm-stt.md
           - TTS: model-deployment/tts.md
           - Support Matrix: model-deployment/support-matrix.md
@@ -342,6 +344,7 @@ nav:
           - FasterLivePortrait: model-deployment/fasterliveportrait.md
       - Recipes:
           - Local Audio + QuickTalk: model-deployment/recipes/local-quicktalk-audio.md
+          - V100 + FasterLivePortrait + FlashHead: model-deployment/recipes/v100-fasterliveportrait-flashhead.md
       - LLM and STT: model-deployment/llm-stt.md
       - TTS: model-deployment/tts.md
       - Support Matrix: model-deployment/support-matrix.md