Enable CodeGen vLLM (#1636)

Signed-off-by: Wang, Xigui <xigui.wang@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml

@@ -5,6 +5,8 @@ services:
   tgi-service:
     image: ghcr.io/huggingface/tgi-gaudi:2.3.1
     container_name: tgi-gaudi-server
+    profiles:
+      - codegen-gaudi-tgi
     ports:
       - "8028:80"
     volumes:
@@ -30,28 +32,74 @@ services:
       - SYS_NICE
     ipc: host
     command: --model-id ${LLM_MODEL_ID} --max-input-length 1024 --max-total-tokens 2048
-  llm:
-    image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest}
-    container_name: llm-textgen-gaudi-server
-    depends_on:
-      tgi-service:
-        condition: service_healthy
+  vllm-service:
+    image: ${REGISTRY:-opea}/vllm-gaudi:${TAG:-latest}
+    container_name: vllm-gaudi-server
+    profiles:
+      - codegen-gaudi-vllm
     ports:
-      - "9000:9000"
-    ipc: host
+      - "8028:80"
+    volumes:
+      - "${MODEL_CACHE:-./data}:/root/.cache/huggingface/hub"
+    shm_size: 1g
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
+      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      HABANA_VISIBLE_DEVICES: all
+      OMPI_MCA_btl_vader_single_copy_mechanism: none
+      VLLM_SKIP_WARMUP: ${VLLM_SKIP_WARMUP:-false}
+      NUM_CARDS: ${NUM_CARDS:-1}
+      VLLM_TORCH_PROFILER_DIR: "/mnt"
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://$host_ip:8028/health || exit 1"]
+      interval: 10s
+      timeout: 10s
+      retries: 100
+    runtime: habana
+    cap_add:
+      - SYS_NICE
+    ipc: host
+    command: --model ${LLM_MODEL_ID} --tensor-parallel-size ${NUM_CARDS} --host 0.0.0.0 --port 80 --block-size 128 --max-num-seqs 256
+  llm-base:
+    image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest}
+    container_name: llm-textgen-gaudi-server
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      LLM_ENDPOINT: ${LLM_ENDPOINT}
       LLM_MODEL_ID: ${LLM_MODEL_ID}
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
     restart: unless-stopped
+  llm-tgi-service:
+    extends: llm-base
+    container_name: llm-codegen-tgi-gaudi-server
+    profiles:
+      - codegen-gaudi-tgi
+    ports:
+      - "9000:9000"
+    ipc: host
+    depends_on:
+      tgi-service:
+        condition: service_healthy
+  llm-vllm-service:
+    extends: llm-base
+    container_name: llm-codegen-gaudi-vllm-server
+    profiles:
+      - codegen-gaudi-vllm
+    ports:
+      - "9000:9000"
+    ipc: host
+    depends_on:
+      vllm-service:
+        condition: service_healthy
   codegen-gaudi-backend-server:
     image: ${REGISTRY:-opea}/codegen:${TAG:-latest}
     container_name: codegen-gaudi-backend-server
     depends_on:
-      - llm
+      - llm-base
     ports:
       - "7778:7778"
     environment: