Translation App - Adding files to deploy Translation application on AMD GPU (#1191)

Signed-off-by: artem-astafev <a.astafev@datamonsters.com>
2025-01-02 08:19:44 +07:00
parent cc1d97f816
commit 75b0961a48
4 changed files with 426 additions and 0 deletions
--- a/Translation/docker_compose/amd/gpu/rocm/README.md
+++ b/Translation/docker_compose/amd/gpu/rocm/README.md
@@ -0,0 +1,128 @@
+# Build and deploy Translation Application on AMD GPU (ROCm)
+
+## Build images
+
+### Build the LLM Docker Image
+
+```bash
+### Cloning repo
+git clone https://github.com/opea-project/GenAIComps.git
+cd GenAIComps
+
+### Build Docker image
+docker build -t opea/llm-tgi:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f comps/llms/text-generation/tgi/Dockerfile .
+```
+
+### Build the MegaService Docker Image
+
+```bash
+### Cloning repo
+git clone https://github.com/opea-project/GenAIExamples
+cd GenAIExamples/Translation/
+
+### Build Docker image
+docker build -t opea/translation:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+```
+
+### Build the UI Docker Image
+
+```bash
+cd GenAIExamples/Translation/ui
+### Build UI Docker image
+docker build -t opea/translation-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f docker/Dockerfile .
+```
+
+## Deploy Translation Application
+
+### Features of Docker compose for AMD GPUs
+
+1. Added forwarding of GPU devices to the container TGI service with instructions:
+
+```yaml
+shm_size: 1g
+devices:
+  - /dev/kfd:/dev/kfd
+  - /dev/dri/:/dev/dri/
+cap_add:
+  - SYS_PTRACE
+group_add:
+  - video
+security_opt:
+  - seccomp:unconfined
+```
+
+In this case, all GPUs are thrown. To reset a specific GPU, you need to use specific device names cardN and renderN.
+
+For example:
+
+```yaml
+shm_size: 1g
+devices:
+  - /dev/kfd:/dev/kfd
+  - /dev/dri/card0:/dev/dri/card0
+  - /dev/dri/render128:/dev/dri/render128
+cap_add:
+  - SYS_PTRACE
+group_add:
+  - video
+security_opt:
+  - seccomp:unconfined
+```
+
+To find out which GPU device IDs cardN and renderN correspond to the same GPU, use the GPU driver utility
+
+### Go to the directory with the Docker compose file
+
+```bash
+cd GenAIExamples/Translation/docker_compose/amd/gpu/rocm
+```
+
+### Set environments
+
+In the file "GenAIExamples/Translation/docker_compose/amd/gpu/rocm/set_env.sh " it is necessary to set the required values. Parameter assignments are specified in the comments for each variable setting command
+
+```bash
+chmod +x set_env.sh
+. set_env.sh
+```
+
+### Run services
+
+```
+docker compose up -d
+```
+
+# Validate the MicroServices and MegaService
+
+## Validate TGI service
+
+```bash
+curl http://${TRANSLATION_HOST_IP}:${TRANSLATIONS_TGI_SERVICE_PORT}/generate \
+  -X POST \
+  -d '{"inputs":"What is Deep Learning?","parameters":{"max_new_tokens":17, "do_sample": true}}' \
+  -H 'Content-Type: application/json'
+```
+
+## Validate LLM service
+
+```bash
+curl http://${TRANSLATION_HOST_IP}:9000/v1/chat/completions \
+  -X POST \
+  -d '{"query":"Translate this from Chinese to English:\nChinese: 我爱机器翻译。\nEnglish:"}' \
+  -H 'Content-Type: application/json'
+```
+
+## Validate MegaService
+
+```bash
+curl http://${TRANSLATION_HOST_IP}:${TRANSLATION_BACKEND_SERVICE_PORT}/v1/translation -H "Content-Type: application/json" -d '{
+     "language_from": "Chinese","language_to": "English","source_language": "我爱机器翻译。"}'
+```
+
+## Validate Nginx service
+
+```bash
+curl http://${TRANSLATION_HOST_IP}:${TRANSLATION_NGINX_PORT}/v1/translation \
+    -H "Content-Type: application/json" \
+    -d '{"language_from": "Chinese","language_to": "English","source_language": "我爱机器翻译。"}'
+```
--- a/Translation/docker_compose/amd/gpu/rocm/compose.yaml
+++ b/Translation/docker_compose/amd/gpu/rocm/compose.yaml
@@ -0,0 +1,99 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+services:
+  translation-tgi-service:
+    image: ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
+    container_name: translation-tgi-service
+    ports:
+      - "${TRANSLATION_TGI_SERVICE_PORT:-8008}:80"
+    volumes:
+      - "/var/lib/GenAI/translation/data:/data"
+    shm_size: 8g
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      TGI_LLM_ENDPOINT: ${TRANSLATION_TGI_LLM_ENDPOINT}
+      HUGGING_FACE_HUB_TOKEN: ${TRANSLATION_HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${TRANSLATION_HUGGINGFACEHUB_API_TOKEN}
+    devices:
+      - /dev/kfd:/dev/kfd
+      - /dev/dri/:/dev/dri/
+    cap_add:
+      - SYS_PTRACE
+    group_add:
+      - video
+    security_opt:
+      - seccomp:unconfined
+    ipc: host
+    command: --model-id ${TRANSLATION_LLM_MODEL_ID}
+  translation-llm:
+    image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
+    container_name: translation-llm-tgi-server
+    depends_on:
+      - translation-tgi-service
+    ports:
+      - "9000:9000"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      TGI_LLM_ENDPOINT: ${TRANSLATION_TGI_LLM_ENDPOINT}
+      HUGGINGFACEHUB_API_TOKEN: ${TRANSLATION_HUGGINGFACEHUB_API_TOKEN}
+      HF_HUB_DISABLE_PROGRESS_BARS: 1
+      HF_HUB_ENABLE_HF_TRANSFER: 0
+    restart: unless-stopped
+  translation-backend-server:
+    image: ${REGISTRY:-opea}/translation:${TAG:-latest}
+    container_name: translation-backend-server
+    depends_on:
+      - translation-tgi-service
+      - translation-llm
+    ports:
+      - "${TRANSLATION_BACKEND_SERVICE_PORT:-8888}:8888"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - MEGA_SERVICE_HOST_IP=${TRANSLATION_MEGA_SERVICE_HOST_IP}
+      - LLM_SERVICE_HOST_IP=${TRANSLATION_LLM_SERVICE_HOST_IP}
+    ipc: host
+    restart: always
+  translation-ui-server:
+    image: ${REGISTRY:-opea}/translation-ui:${TAG:-latest}
+    container_name: translation-ui-server
+    depends_on:
+      - translation-backend-server
+    ports:
+      - "${TRANSLATION_FRONTEND_SERVICE_PORT:-5173}:5173"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - BASE_URL=${TRANSLATION_BACKEND_SERVICE_ENDPOINT}
+    ipc: host
+    restart: always
+  translation-nginx-server:
+    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
+    container_name: translation-nginx-server
+    depends_on:
+      - translation-backend-server
+      - translation-ui-server
+    ports:
+      - "${TRANSLATION_NGINX_PORT:-80}:80"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - FRONTEND_SERVICE_IP=${TRANSLATION_FRONTEND_SERVICE_IP}
+      - FRONTEND_SERVICE_PORT=${TRANSLATION_FRONTEND_SERVICE_PORT}
+      - BACKEND_SERVICE_NAME=${TRANSLATION_BACKEND_SERVICE_NAME}
+      - BACKEND_SERVICE_IP=${TRANSLATION_BACKEND_SERVICE_IP}
+      - BACKEND_SERVICE_PORT=${TRANSLATION_BACKEND_SERVICE_PORT}
+    ipc: host
+    restart: always
+networks:
+  default:
+    driver: bridge
--- a/Translation/docker_compose/amd/gpu/rocm/set_env.sh
+++ b/Translation/docker_compose/amd/gpu/rocm/set_env.sh
@@ -0,0 +1,21 @@
+#!/usr/bin/env bash
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+# SPDX-License-Identifier: Apache-2.0
+
+export TRANSLATION_HOST_IP=''
+export TRANSLATION_EXTERNAL_HOST_IP=''
+export TRANSLATION_LLM_MODEL_ID="haoranxu/ALMA-13B"
+export TRANSLATION_TGI_LLM_ENDPOINT="http://${TRANSLATION_HOST_IP}:8008"
+export TRANSLATION_HUGGINGFACEHUB_API_TOKEN=''
+export TRANSLATION_MEGA_SERVICE_HOST_IP=${TRANSLATION_HOST_IP}
+export TRANSLATION_LLM_SERVICE_HOST_IP=${TRANSLATION_HOST_IP}
+export TRANSLATION_FRONTEND_SERVICE_IP=${TRANSLATION_HOST_IP}
+export TRANSLATION_FRONTEND_SERVICE_PORT=18122
+export TRANSLATION_BACKEND_SERVICE_NAME=translation
+export TRANSLATION_BACKEND_SERVICE_IP=${TRANSLATION_HOST_IP}
+export TRANSLATION_BACKEND_SERVICE_PORT=18121
+export TRANSLATION_BACKEND_SERVICE_ENDPOINT="http://${TRANSLATION_EXTERNAL_HOST_IP}:${TRANSLATION_BACKEND_SERVICE_PORT}/v1/translation"
+export TRANSLATION_NGINX_PORT=18123