diff --git a/CodeGen/docker_compose/amd/gpu/rocm/compose.yaml b/CodeGen/docker_compose/amd/gpu/rocm/compose.yaml
index cf7d2369c4..ffcbb4867b 100644
--- a/CodeGen/docker_compose/amd/gpu/rocm/compose.yaml
+++ b/CodeGen/docker_compose/amd/gpu/rocm/compose.yaml
@@ -15,6 +15,12 @@ services:
       https_proxy: ${https_proxy}
       HUGGING_FACE_HUB_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
       HUGGINGFACEHUB_API_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
+      host_ip: ${host_ip}
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://$host_ip:8008/health || exit 1"]
+      interval: 10s
+      timeout: 10s
+      retries: 100
     shm_size: 1g
     devices:
       - /dev/kfd:/dev/kfd
@@ -31,7 +37,8 @@ services:
     image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
     container_name: codegen-llm-server
     depends_on:
-      - codegen-tgi-service
+      codegen-tgi-service:
+        condition: service_healthy
     ports:
       - "${CODEGEN_LLM_SERVICE_PORT:-9000}:9000"
     ipc: host
@@ -39,7 +46,8 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      TGI_LLM_ENDPOINT: "http://codegen-tgi-service"
+      LLM_ENDPOINT: "http://codegen-tgi-service"
+      LLM_MODEL_ID: ${LLM_MODEL_ID}
       HUGGINGFACEHUB_API_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
     restart: unless-stopped
   codegen-backend-server:
diff --git a/CodeGen/docker_compose/intel/cpu/xeon/compose.yaml b/CodeGen/docker_compose/intel/cpu/xeon/compose.yaml
index 64b74db71f..6d62260a83 100644
--- a/CodeGen/docker_compose/intel/cpu/xeon/compose.yaml
+++ b/CodeGen/docker_compose/intel/cpu/xeon/compose.yaml
@@ -15,12 +15,19 @@ services:
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
       HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      host_ip: ${host_ip}
+    healthcheck:
+      test: ["CMD-SHELL", "curl -f http://$host_ip:8008/health || exit 1"]
+      interval: 10s
+      timeout: 10s
+      retries: 100
     command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0
   llm:
     image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
     container_name: llm-tgi-server
     depends_on:
-      - tgi-service
+      tgi-service:
+        condition: service_healthy
     ports:
       - "9000:9000"
     ipc: host
@@ -28,7 +35,8 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
+      LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
+      LLM_MODEL_ID: ${LLM_MODEL_ID}
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
     restart: unless-stopped
   codegen-xeon-backend-server:
diff --git a/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml b/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml
index 92b70b099c..7f7e71295a 100644
--- a/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml
+++ b/CodeGen/docker_compose/intel/hpu/gaudi/compose.yaml
@@ -20,6 +20,11 @@ services:
       LIMIT_HPU_GRAPH: true
       USE_FLASH_ATTENTION: true
       FLASH_ATTENTION_RECOMPUTE: true
+    healthcheck:
+      test: ["CMD-SHELL", "sleep 500 && exit 0"]
+      interval: 1s
+      timeout: 505s
+      retries: 1
     runtime: habana
     cap_add:
       - SYS_NICE
@@ -29,7 +34,8 @@ services:
     image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
     container_name: llm-tgi-gaudi-server
     depends_on:
-      - tgi-service
+      tgi-service:
+        condition: service_healthy
     ports:
       - "9000:9000"
     ipc: host
@@ -37,7 +43,8 @@ services:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
+      LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
+      LLM_MODEL_ID: ${LLM_MODEL_ID}
       HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
     restart: unless-stopped
   codegen-gaudi-backend-server: