Agent 2.0 exdev 서버 배포 스택

- server-dev start/stop/deploy 및 Gitea push 자동 배포
- local-dev 로컬 개발 환경

Co-authored-by: Cursor <cursoragent@cursor.com>

exAiChatBot-chatbot2.0-agent/llmServer/docker 실행 명령어

@@ -0,0 +1,78 @@
+=========== embedding ===========
+
+docker run -d --gpus all \
+  --name tei-embedding \
+  -p 16001:80 \
+  -v /DATA/exlink/models:/data \
+  --pull never \
+  --restart always \
+  ghcr.io/huggingface/text-embeddings-inference:hopper-1.8 \
+  --model-id /data/qwen3-embedding-8b \
+  --port 80 \
+  --max-batch-tokens 40960
+
+
+curl 127.0.0.1:16001/embed \
+  -X POST \
+  -d '{"inputs":"안녕하세요, 임베딩 테스트 중입니다."}' \
+  -H 'Content-Type: application/json'
+=========== embedding ===========
+
+=========== reranker ===========
+
+docker rm -f vllm-reranker
+
+docker rm -f vllm-reranker
+
+docker run -d --gpus all \
+  --name vllm-reranker \
+  -p 16002:8000 \
+  -v /DATA/exlink/models:/data \
+  --ipc=host \
+  --restart always \
+  -e HF_HUB_OFFLINE=1 \
+  -e TRANSFORMERS_OFFLINE=1 \
+  vllm/vllm-openai:latest \
+  python3 /data/reranker_server.py
+
+curl http://127.0.0.1:16002/v1/rerank \
+  -X POST \
+  -H "Content-Type: application/json" \
+  -d '{
+"model": "/data/qwen3-reranker-4b",
+"query": "사과는 어떤 과일인가요?",
+"documents": [
+"사과는 빨간색 과일이며 비타민이 풍부합니다.",
+"서울은 대한민국의 수도입니다."
+]
+}'
+=========== reranker ===========
+
+
+=========== LLM ===========
+
+docker run -d --gpus all \ 
+  --name vllm-server \ 
+  --memory 32g \ 
+  -p 16000:8000 \ 
+  -v /DATA/exlink/models:/data \ 
+  --ipc=host \ --restart always \ 
+  --network bridge \ 
+  -e HF_HUB_OFFLINE=1 \ 
+  -e HF_HOME=/data/cache \ 
+  -e TRANSFORMERS_OFFLINE=1 \ 
+  --entrypoint python3 \ 
+  vllm/vllm-openai:latest \ 
+  -m vllm.entrypoints.openai.api_server \ 
+  --model /data/Qwen3.5-27B-FP8 \ 
+  --host 0.0.0.0 \ 
+  --port 8000 \ 
+  --gpu-memory-utilization 0.65 \ 
+  --max-model-len 5120 \ 
+  --max-num-seqs 8 \ 
+  --enable-chunked-prefill \ 
+  --max-num-batched-tokens 4096 \ 
+
+  =========== LLM ===========
+
+