Enable vllm for DocSum (#1716)

Set vllm as default llm serving, and add related docker compose files, readmes, and test scripts.

Fix issue #1436

Signed-off-by: letonghan <letong.han@intel.com>
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>

DocSum/docker_compose/intel/cpu/xeon/compose.yaml

@@ -2,54 +2,53 @@
 # SPDX-License-Identifier: Apache-2.0
 
 services:
-  tgi-server:
-    image: ghcr.io/huggingface/text-generation-inference:2.4.0-intel-cpu
-    container_name: tgi-server
+  vllm-service:
+    image: ${REGISTRY:-opea}/vllm:${TAG:-latest}
+    container_name: docsum-xeon-vllm-service
     ports:
-      - ${LLM_ENDPOINT_PORT:-8008}:80
+      - "8008:80"
+    volumes:
+      - "${MODEL_CACHE:-./data}:/root/.cache/huggingface/hub"
+    shm_size: 1g
     environment:
       no_proxy: ${no_proxy}
       http_proxy: ${http_proxy}
       https_proxy: ${https_proxy}
-      TGI_LLM_ENDPOINT: ${TGI_LLM_ENDPOINT}
-      HUGGINGFACEHUB_API_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
-      host_ip: ${host_ip}
-      LLM_ENDPOINT_PORT: ${LLM_ENDPOINT_PORT}
+      HF_TOKEN: ${HUGGINGFACEHUB_API_TOKEN}
+      LLM_MODEL_ID: ${LLM_MODEL_ID}
+      VLLM_TORCH_PROFILER_DIR: "/mnt"
     healthcheck:
-      test: ["CMD-SHELL", "curl -f http://${host_ip}:${LLM_ENDPOINT_PORT}/health || exit 1"]
+      test: ["CMD-SHELL", "curl -f http://localhost:80/health || exit 1"]
       interval: 10s
       timeout: 10s
       retries: 100
-    volumes:
-      - "${MODEL_CACHE:-./data}:/data"
-    shm_size: 1g
-    command: --model-id ${LLM_MODEL_ID} --cuda-graphs 0  --max-input-length ${MAX_INPUT_TOKENS} --max-total-tokens ${MAX_TOTAL_TOKENS}
+    command: --model $LLM_MODEL_ID --host 0.0.0.0 --port 80
 
-  llm-docsum-tgi:
+  llm-docsum-vllm:
     image: ${REGISTRY:-opea}/llm-docsum:${TAG:-latest}
-    container_name: llm-docsum-server
+    container_name: docsum-xeon-llm-server
     depends_on:
-      tgi-server:
+      vllm-service:
         condition: service_healthy
     ports:
-      - ${DOCSUM_PORT:-9000}:9000
+      - ${LLM_PORT:-9000}:9000
     ipc: host
     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}
       MAX_INPUT_TOKENS: ${MAX_INPUT_TOKENS}
       MAX_TOTAL_TOKENS: ${MAX_TOTAL_TOKENS}
-      LLM_MODEL_ID: ${LLM_MODEL_ID}
       DocSum_COMPONENT_NAME: ${DocSum_COMPONENT_NAME}
       LOGFLAG: ${LOGFLAG:-False}
     restart: unless-stopped
 
   whisper:
     image: ${REGISTRY:-opea}/whisper:${TAG:-latest}
-    container_name: whisper-server
+    container_name: docsum-xeon-whisper-server
     ports:
       - "7066:7066"
     ipc: host
@@ -63,10 +62,10 @@ services:
     image: ${REGISTRY:-opea}/docsum:${TAG:-latest}
     container_name: docsum-xeon-backend-server
     depends_on:
-      - tgi-server
-      - llm-docsum-tgi
+      - vllm-service
+      - llm-docsum-vllm
     ports:
-      - "8888:8888"
+      - "${BACKEND_SERVICE_PORT:-8888}:8888"
     environment:
       - no_proxy=${no_proxy}
       - https_proxy=${https_proxy}
@@ -83,7 +82,7 @@ services:
     depends_on:
       - docsum-xeon-backend-server
     ports:
-      - "5173:5173"
+      - "${FRONTEND_SERVICE_PORT:-5173}:5173"
     environment:
       - no_proxy=${no_proxy}
       - https_proxy=${https_proxy}