Files
chyundunovDatamonsters 31b1d69e40 Adding files to deploy CodeGen application on ROCm vLLM (#1544)
Signed-off-by: Chingis Yundunov <YundunovCN@sibedge.com>
2025-03-24 14:45:17 +08:00

95 lines
3.0 KiB
YAML

# Copyright (C) 2024 Intel Corporation
# Copyright (c) 2024 Advanced Micro Devices, Inc.
# SPDX-License-Identifier: Apache-2.0
services:
codegen-vllm-service:
image: ${REGISTRY:-opea}/vllm-rocm:${TAG:-latest}
container_name: codegen-vllm-service
ports:
- "${CODEGEN_VLLM_SERVICE_PORT:-8081}:8011"
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
HUGGINGFACEHUB_API_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
HF_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
HF_HUB_DISABLE_PROGRESS_BARS: 1
HF_HUB_ENABLE_HF_TRANSFER: 0
WILM_USE_TRITON_FLASH_ATTENTION: 0
PYTORCH_JIT: 0
healthcheck:
test: [ "CMD-SHELL", "curl -f http://${HOST_IP}:${CODEGEN_VLLM_SERVICE_PORT:-8028}/health || exit 1" ]
interval: 10s
timeout: 10s
retries: 100
volumes:
- "./data:/data"
shm_size: 20G
devices:
- /dev/kfd:/dev/kfd
- /dev/dri/:/dev/dri/
cap_add:
- SYS_PTRACE
group_add:
- video
security_opt:
- seccomp:unconfined
- apparmor=unconfined
command: "--model ${CODEGEN_LLM_MODEL_ID} --swap-space 16 --disable-log-requests --dtype float16 --tensor-parallel-size 4 --host 0.0.0.0 --port 8011 --num-scheduler-steps 1 --distributed-executor-backend \"mp\""
ipc: host
codegen-llm-server:
image: ${REGISTRY:-opea}/llm-textgen:${TAG:-latest}
container_name: codegen-llm-server
depends_on:
codegen-vllm-service:
condition: service_healthy
ports:
- "${CODEGEN_LLM_SERVICE_PORT:-9000}:9000"
ipc: host
environment:
no_proxy: ${no_proxy}
http_proxy: ${http_proxy}
https_proxy: ${https_proxy}
LLM_ENDPOINT: ${CODEGEN_VLLM_ENDPOINT}
LLM_MODEL_ID: ${CODEGEN_LLM_MODEL_ID}
HUGGINGFACEHUB_API_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
HF_TOKEN: ${CODEGEN_HUGGINGFACEHUB_API_TOKEN}
LLM_COMPONENT_NAME: "OpeaTextGenService"
restart: unless-stopped
codegen-backend-server:
image: ${REGISTRY:-opea}/codegen:${TAG:-latest}
container_name: codegen-backend-server
depends_on:
- codegen-llm-server
ports:
- "${CODEGEN_BACKEND_SERVICE_PORT:-7778}:7778"
environment:
no_proxy: ${no_proxy}
https_proxy: ${https_proxy}
http_proxy: ${http_proxy}
MEGA_SERVICE_HOST_IP: ${CODEGEN_MEGA_SERVICE_HOST_IP}
LLM_SERVICE_HOST_IP: ${HOST_IP}
LLM_SERVICE_PORT: ${CODEGEN_LLM_SERVICE_PORT}
ipc: host
restart: always
codegen-ui-server:
image: ${REGISTRY:-opea}/codegen-ui:${TAG:-latest}
container_name: codegen-ui-server
depends_on:
- codegen-backend-server
ports:
- "${CODEGEN_UI_SERVICE_PORT:-5173}:5173"
environment:
no_proxy: ${no_proxy}
https_proxy: ${https_proxy}
http_proxy: ${http_proxy}
BASIC_URL: ${CODEGEN_BACKEND_SERVICE_URL}
BACKEND_SERVICE_ENDPOINT: ${CODEGEN_BACKEND_SERVICE_URL}
ipc: host
restart: always
networks:
default:
driver: bridge