Adding files to deploy CodeTrans application on AMD GPU

CodeTrans/docker_compose/amd/gpu/rocm/README.md

@@ -0,0 +1,121 @@
+# Build and deploy CodeTrans 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/CodeTrans
+
+### Build Docker image
+docker build -t opea/codetrans:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f Dockerfile .
+```
+
+### Build the UI Docker Image
+
+```bash
+cd GenAIExamples/CodeTrans/ui
+### Build UI Docker image
+docker build -t opea/codetrans-ui:latest --build-arg https_proxy=$https_proxy --build-arg http_proxy=$http_proxy -f ./docker/Dockerfile .
+```
+
+## Deploy CodeTrans 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/CodeTrans/docker_compose/amd/gpu/rocm
+```
+
+### Set environments
+
+In the file "GenAIExamples/CodeTrans/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://${HOST_IP}:${CODETRANS_TGI_SERVICE_PORT}/generate \
+  -X POST \
+  -d '{"inputs":"    ### System: Please translate the following Golang codes into  Python codes.    ### Original codes:    '\'''\'''\''Golang    \npackage main\n\nimport \"fmt\"\nfunc main() {\n    fmt.Println(\"Hello, World!\");\n    '\'''\'''\''    ### Translated codes:","parameters":{"max_new_tokens":17, "do_sample": true}}' \
+  -H 'Content-Type: application/json'
+```
+
+## Validate LLM service
+
+```bash
+curl http://${HOST_IP}:${CODETRANS_LLM_SERVICE_PORT}/v1/chat/completions \
+  -X POST \
+  -d '{"query":"    ### System: Please translate the following Golang codes into  Python codes.    ### Original codes:    '\'''\'''\''Golang    \npackage main\n\nimport \"fmt\"\nfunc main() {\n    fmt.Println(\"Hello, World!\");\n    '\'''\'''\''    ### Translated codes:"}' \
+  -H 'Content-Type: application/json'
+```
+
+## Validate MegaService
+
+```bash
+curl http://${HOST_IP}:${CODEGEN_BACKEND_SERVICE_PORT}/v1/codetrans \
+  -H "Content-Type: application/json" \
+  -d '{"language_from": "Golang","language_to": "Python","source_code": "package main\n\nimport \"fmt\"\nfunc main() {\n    fmt.Println(\"Hello, World!\");\n}"}'
+```

CodeTrans/docker_compose/amd/gpu/rocm/compose.yaml

@@ -0,0 +1,97 @@
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+services:
+  codetrans-tgi-service:
+    image: ghcr.io/huggingface/text-generation-inference:2.3.1-rocm
+    container_name: codetrans-tgi-service
+    ports:
+      - "${CODETRANS_TGI_SERVICE_PORT:-8008}:80"
+    volumes:
+      - "/var/lib/GenAI/codetrans/data:/data"
+    shm_size: 1g
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      TGI_LLM_ENDPOINT: ${CODETRANS_TGI_LLM_ENDPOINT}
+      HUGGING_FACE_HUB_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
+      HUGGINGFACEHUB_API_TOKEN: ${CODEGEN_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 ${CODETRANS_LLM_MODEL_ID}
+  codetrans-llm-server:
+    image: ${REGISTRY:-opea}/llm-tgi:${TAG:-latest}
+    container_name: codetrans-llm-server
+    ports:
+      - "${CODETRANS_LLM_SERVICE_PORT:-9000}:9000"
+    ipc: host
+    environment:
+      no_proxy: ${no_proxy}
+      http_proxy: ${http_proxy}
+      https_proxy: ${https_proxy}
+      TGI_LLM_ENDPOINT: "http://codetrans-tgi-service"
+      HUGGINGFACEHUB_API_TOKEN: ${CODETRANS_HUGGINGFACEHUB_API_TOKEN}
+    restart: unless-stopped
+  codetrans-backend-server:
+    image: ${REGISTRY:-opea}/codetrans:${TAG:-latest}
+    container_name: codetrans-backend-server
+    depends_on:
+      - codetrans-tgi-service
+      - codetrans-llm-server
+    ports:
+      - "${CODETRANS_BACKEND_SERVICE_PORT:-7777}:7777"
+    environment:
+      no_proxy: ${no_proxy}
+      https_proxy: ${https_proxy}
+      http_proxy: ${http_proxy}
+      MEGA_SERVICE_HOST_IP: ${HOST_IP}
+      LLM_SERVICE_HOST_IP: "codetrans-llm-server"
+    ipc: host
+    restart: always
+  codetrans-ui-server:
+    image: ${REGISTRY:-opea}/codetrans-ui:${TAG:-latest}
+    container_name: codetrans-ui-server
+    depends_on:
+      - codetrans-backend-server
+    ports:
+      - "${CODETRANS_FRONTEND_SERVICE_PORT:-5173}:5173"
+    environment:
+      no_proxy: ${no_proxy}
+      https_proxy: ${https_proxy}
+      http_proxy: ${http_proxy}
+      BASE_URL: ${CODETRANS_BACKEND_SERVICE_URL}
+      BASIC_URL: ${CODETRANS_BACKEND_SERVICE_URL}
+    ipc: host
+    restart: always
+  codetrans-nginx-server:
+    image: ${REGISTRY:-opea}/nginx:${TAG:-latest}
+    container_name: codetrans-nginx-server
+    depends_on:
+      - codetrans-backend-server
+      - codetrans-ui-server
+    ports:
+      - "${CODETRANS_NGINX_PORT:-80}:80"
+    environment:
+      - no_proxy=${no_proxy}
+      - https_proxy=${https_proxy}
+      - http_proxy=${http_proxy}
+      - FRONTEND_SERVICE_IP=${CODETRANS_FRONTEND_SERVICE_IP}
+      - FRONTEND_SERVICE_PORT=${CODETRANS_FRONTEND_SERVICE_PORT}
+      - BACKEND_SERVICE_NAME=${CODETRANS_BACKEND_SERVICE_NAME}
+      - BACKEND_SERVICE_IP=${CODETRANS_BACKEND_SERVICE_IP}
+      - BACKEND_SERVICE_PORT=${CODETRANS_BACKEND_SERVICE_PORT}
+    ipc: host
+    restart: always
+
+networks:
+  default:
+    driver: bridge

CodeTrans/docker_compose/amd/gpu/rocm/set_env.sh

@@ -0,0 +1,49 @@
+#!/usr/bin/env bash
+
+# Copyright (C) 2024 Intel Corporation
+# SPDX-License-Identifier: Apache-2.0
+
+### The IP address or domain name of the server on which the application is running
+export HOST_IP=direct-supercomputer1.powerml.co
+
+### Model ID
+export CODETRANS_LLM_MODEL_ID="Qwen/Qwen2.5-Coder-7B-Instruct"
+
+### The port of the TGI service. On this port, the TGI service will accept connections
+export CODETRANS_TGI_SERVICE_PORT=18156
+
+### The endpoint of the TGI service to which requests to this service will be sent (formed from previously set variables)
+export CODETRANS_TGI_LLM_ENDPOINT="http://${HOST_IP}:${CODETRANS_TGI_SERVICE_PORT}"
+
+### A token for accessing repositories with models
+export CODETRANS_HUGGINGFACEHUB_API_TOKEN=''
+
+### The port of the LLM service. On this port, the LLM service will accept connections
+export CODETRANS_LLM_SERVICE_PORT=18157
+
+### The IP address or domain name of the server for CodeTrans MegaService
+export CODETRANS_MEGA_SERVICE_HOST_IP=${HOST_IP}
+
+### The endpoint of the LLM service to which requests to this service will be sent
+export CODETRANS_LLM_SERVICE_HOST_IP=${HOST_IP}
+
+### The ip address of the host on which the container with the frontend service is running
+export CODETRANS_FRONTEND_SERVICE_IP=192.165.1.21
+
+### The port of the frontend service
+export CODETRANS_FRONTEND_SERVICE_PORT=18155
+
+### Name of GenAI service for route requests to application
+export CODETRANS_BACKEND_SERVICE_NAME=codetrans
+
+### The ip address of the host on which the container with the backend service is running
+export CODETRANS_BACKEND_SERVICE_IP=192.165.1.21
+
+### The port of the backend service
+export CODETRANS_BACKEND_SERVICE_PORT=18154
+
+### The port of the Nginx reverse proxy for application
+export CODETRANS_NGINX_PORT=18153
+
+### Endpoint of the backend service
+export CODETRANS_BACKEND_SERVICE_URL="http://${HOST_IP}:${CODETRANS_BACKEND_SERVICE_PORT}/v1/codetrans"