adelorenzo/portainer_scripts
1
0
Fork 0
Code Issues Pull Requests Projects Releases Wiki Activity

v2

Browse Source
This commit is contained in:
Adolfo Delorenzo
2026-03-10 14:40:51 -03:00
parent 290f05be87
commit 92713a4d1c
30 changed files with 2074 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

30
ai-templates-0/stacks/bentoml/docker-compose.yml Normal file
View File

@@ -0,0 +1,30 @@
version: "3.8"
services:
bentoml:
image: bentoml/bentoml:${BENTO_VERSION:-latest}
container_name: bentoml
restart: unless-stopped
ports:
- "${BENTO_PORT:-3000}:3000"
- "${METRICS_PORT:-3001}:3001"
volumes:
- bentoml_home:/home/bentoml
- bentoml_models:/home/bentoml/bentoml/models
environment:
- BENTOML_HOME=/home/bentoml/bentoml
- BENTOML_PORT=3000
- BENTOML_METRICS_PORT=3001
- BENTOML_LOG_LEVEL=${LOG_LEVEL:-INFO}
command: bentoml serve --host 0.0.0.0 --port 3000
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
volumes:
bentoml_home:
bentoml_models:

20
ai-templates-0/stacks/chromadb/docker-compose.yml Normal file
View File

@@ -0,0 +1,20 @@
version: "3.8"
services:
chromadb:
image: chromadb/chroma:latest
container_name: chromadb
restart: unless-stopped
ports:
- "${CHROMA_PORT:-8000}:8000"
volumes:
- chroma_data:/chroma/chroma
environment:
- IS_PERSISTENT=TRUE
- PERSIST_DIRECTORY=/chroma/chroma
- ANONYMIZED_TELEMETRY=${TELEMETRY:-FALSE}
- CHROMA_SERVER_AUTHN_CREDENTIALS=${CHROMA_TOKEN:-}
- CHROMA_SERVER_AUTHN_PROVIDER=${CHROMA_AUTH_PROVIDER:-}
volumes:
chroma_data:

31
ai-templates-0/stacks/comfyui/docker-compose.yml Normal file
View File

@@ -0,0 +1,31 @@
version: "3.8"
services:
comfyui:
image: yanwk/comfyui-boot:latest
container_name: comfyui
restart: unless-stopped
ports:
- "${COMFYUI_PORT:-8188}:8188"
volumes:
- comfyui_data:/root
- comfyui_models:/root/ComfyUI/models
- comfyui_output:/root/ComfyUI/output
- comfyui_input:/root/ComfyUI/input
- comfyui_custom_nodes:/root/ComfyUI/custom_nodes
environment:
- CLI_ARGS=${CLI_ARGS:---listen 0.0.0.0 --port 8188}
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
volumes:
comfyui_data:
comfyui_models:
comfyui_output:
comfyui_input:
comfyui_custom_nodes:

38
ai-templates-0/stacks/deepstream/docker-compose.yml Normal file
View File

@@ -0,0 +1,38 @@
version: "3.8"
services:
deepstream:
image: nvcr.io/nvidia/deepstream:${DS_VERSION:-7.1}-triton-multiarch
container_name: deepstream
restart: unless-stopped
ports:
- "${RTSP_PORT:-8554}:8554"
- "${REST_PORT:-9000}:9000"
volumes:
- deepstream_apps:/opt/nvidia/deepstream/deepstream/sources/apps
- deepstream_models:/opt/nvidia/deepstream/deepstream/samples/models
- deepstream_configs:/opt/nvidia/deepstream/deepstream/samples/configs
- deepstream_streams:/opt/nvidia/deepstream/deepstream/samples/streams
environment:
- CUDA_VISIBLE_DEVICES=${CUDA_DEVICES:-all}
- DISPLAY=${DISPLAY:-}
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu, video, compute, utility]
runtime: nvidia
network_mode: ${NETWORK_MODE:-bridge}
shm_size: ${SHM_SIZE:-2g}
# Required for video device access on edge nodes
privileged: ${PRIVILEGED:-false}
devices:
- /dev/video0:/dev/video0
volumes:
deepstream_apps:
deepstream_models:
deepstream_configs:
deepstream_streams:

19
ai-templates-0/stacks/flowise/docker-compose.yml Normal file
View File

@@ -0,0 +1,19 @@
version: "3.8"
services:
flowise:
image: flowiseai/flowise:latest
container_name: flowise
restart: unless-stopped
ports:
- "${FLOWISE_PORT:-3000}:3000"
volumes:
- flowise_data:/root/.flowise
environment:
- FLOWISE_USERNAME=${FLOWISE_USERNAME:-admin}
- FLOWISE_PASSWORD=${FLOWISE_PASSWORD:-changeme}
- APIKEY_PATH=/root/.flowise
- LOG_PATH=/root/.flowise/logs
volumes:
flowise_data:

26
ai-templates-0/stacks/jupyter-gpu/docker-compose.yml Normal file
View File

@@ -0,0 +1,26 @@
version: "3.8"
services:
jupyter:
image: quay.io/jupyter/pytorch-notebook:latest
container_name: jupyter-gpu
restart: unless-stopped
ports:
- "${JUPYTER_PORT:-8888}:8888"
volumes:
- jupyter_data:/home/jovyan/work
environment:
- JUPYTER_TOKEN=${JUPYTER_TOKEN:-changeme}
- JUPYTER_ENABLE_LAB=yes
- GRANT_SUDO=${GRANT_SUDO:-yes}
user: root
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
volumes:
jupyter_data:

19
ai-templates-0/stacks/label-studio/docker-compose.yml Normal file
View File

@@ -0,0 +1,19 @@
version: "3.8"
services:
label-studio:
image: heartexlabs/label-studio:latest
container_name: label-studio
restart: unless-stopped
ports:
- "${LS_PORT:-8080}:8080"
volumes:
- label_studio_data:/label-studio/data
environment:
- LABEL_STUDIO_LOCAL_FILES_SERVING_ENABLED=true
- LABEL_STUDIO_LOCAL_FILES_DOCUMENT_ROOT=/label-studio/data/files
- LABEL_STUDIO_USERNAME=${LS_USER:-admin@example.com}
- LABEL_STUDIO_PASSWORD=${LS_PASSWORD:-changeme}
volumes:
label_studio_data:

18
ai-templates-0/stacks/langflow/docker-compose.yml Normal file
View File

@@ -0,0 +1,18 @@
version: "3.8"
services:
langflow:
image: langflowai/langflow:latest
container_name: langflow
restart: unless-stopped
ports:
- "${LANGFLOW_PORT:-7860}:7860"
volumes:
- langflow_data:/app/langflow
environment:
- LANGFLOW_DATABASE_URL=sqlite:////app/langflow/langflow.db
- LANGFLOW_CONFIG_DIR=/app/langflow
- LANGFLOW_AUTO_LOGIN=${AUTO_LOGIN:-true}
volumes:
langflow_data:

33
ai-templates-0/stacks/litellm/docker-compose.yml Normal file
View File

@@ -0,0 +1,33 @@
version: "3.8"
services:
litellm:
image: ghcr.io/berriai/litellm:main-latest
container_name: litellm
restart: unless-stopped
ports:
- "${LITELLM_PORT:-4000}:4000"
volumes:
- litellm_config:/app/config
environment:
- LITELLM_MASTER_KEY=${LITELLM_MASTER_KEY:-sk-master-key}
- LITELLM_LOG_LEVEL=${LOG_LEVEL:-INFO}
- DATABASE_URL=postgresql://${PG_USER:-litellm}:${PG_PASSWORD:-litellm}@litellm-db:5432/${PG_DB:-litellm}
command: --config /app/config/litellm_config.yaml --port 4000
depends_on:
- litellm-db
litellm-db:
image: postgres:16-alpine
container_name: litellm-db
restart: unless-stopped
environment:
- POSTGRES_USER=${PG_USER:-litellm}
- POSTGRES_PASSWORD=${PG_PASSWORD:-litellm}
- POSTGRES_DB=${PG_DB:-litellm}
volumes:
- litellm_pg_data:/var/lib/postgresql/data
volumes:
litellm_config:
litellm_pg_data:

25
ai-templates-0/stacks/localai/docker-compose.yml Normal file
View File

@@ -0,0 +1,25 @@
version: "3.8"
services:
localai:
image: localai/localai:latest-gpu-nvidia-cuda-12
container_name: localai
restart: unless-stopped
ports:
- "${LOCALAI_PORT:-8080}:8080"
volumes:
- localai_models:/build/models
environment:
- THREADS=${THREADS:-4}
- CONTEXT_SIZE=${CONTEXT_SIZE:-4096}
- MODELS_PATH=/build/models
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
volumes:
localai_models:

76
ai-templates-0/stacks/minio-mlops/docker-compose.yml Normal file
View File

@@ -0,0 +1,76 @@
version: "3.8"
services:
mlflow:
image: ghcr.io/mlflow/mlflow:${MLFLOW_VERSION:-latest}
container_name: mlflow-server
restart: unless-stopped
ports:
- "${MLFLOW_PORT:-5000}:5000"
environment:
- MLFLOW_TRACKING_URI=postgresql://${PG_USER:-mlflow}:${PG_PASSWORD:-mlflow}@mlflow-db:5432/${PG_DB:-mlflow}
- MLFLOW_S3_ENDPOINT_URL=http://mlflow-minio:9000
- AWS_ACCESS_KEY_ID=${MINIO_ROOT_USER:-mlflow}
- AWS_SECRET_ACCESS_KEY=${MINIO_ROOT_PASSWORD:-mlflow123}
- MLFLOW_DEFAULT_ARTIFACT_ROOT=s3://${ARTIFACT_BUCKET:-mlflow-artifacts}/
command: >
mlflow server
--host 0.0.0.0
--port 5000
--backend-store-uri postgresql://${PG_USER:-mlflow}:${PG_PASSWORD:-mlflow}@mlflow-db:5432/${PG_DB:-mlflow}
--default-artifact-root s3://${ARTIFACT_BUCKET:-mlflow-artifacts}/
--serve-artifacts
depends_on:
mlflow-db:
condition: service_healthy
mlflow-minio:
condition: service_started
mlflow-db:
image: postgres:16-alpine
container_name: mlflow-db
restart: unless-stopped
environment:
- POSTGRES_USER=${PG_USER:-mlflow}
- POSTGRES_PASSWORD=${PG_PASSWORD:-mlflow}
- POSTGRES_DB=${PG_DB:-mlflow}
volumes:
- mlflow_pg_data:/var/lib/postgresql/data
healthcheck:
test: ["CMD-SHELL", "pg_isready -U ${PG_USER:-mlflow}"]
interval: 10s
timeout: 5s
retries: 5
mlflow-minio:
image: quay.io/minio/minio:latest
container_name: mlflow-minio
restart: unless-stopped
ports:
- "${MINIO_API_PORT:-9000}:9000"
- "${MINIO_CONSOLE_PORT:-9001}:9001"
volumes:
- mlflow_minio_data:/data
environment:
- MINIO_ROOT_USER=${MINIO_ROOT_USER:-mlflow}
- MINIO_ROOT_PASSWORD=${MINIO_ROOT_PASSWORD:-mlflow123}
command: server /data --console-address ':9001'
# Init container to create the default bucket
mlflow-minio-init:
image: quay.io/minio/mc:latest
container_name: mlflow-minio-init
depends_on:
- mlflow-minio
entrypoint: >
/bin/sh -c "
sleep 5;
mc alias set myminio http://mlflow-minio:9000 ${MINIO_ROOT_USER:-mlflow} ${MINIO_ROOT_PASSWORD:-mlflow123};
mc mb --ignore-existing myminio/${ARTIFACT_BUCKET:-mlflow-artifacts};
mc anonymous set download myminio/${ARTIFACT_BUCKET:-mlflow-artifacts};
exit 0;
"
volumes:
mlflow_pg_data:
mlflow_minio_data:

20
ai-templates-0/stacks/mlflow/docker-compose.yml Normal file
View File

@@ -0,0 +1,20 @@
version: "3.8"
services:
mlflow:
image: ghcr.io/mlflow/mlflow:latest
container_name: mlflow
restart: unless-stopped
ports:
- "${MLFLOW_PORT:-5000}:5000"
volumes:
- mlflow_data:/mlflow
command: >
mlflow server
--host 0.0.0.0
--port 5000
--backend-store-uri sqlite:///mlflow/mlflow.db
--default-artifact-root /mlflow/artifacts
volumes:
mlflow_data:

20
ai-templates-0/stacks/n8n-ai/docker-compose.yml Normal file
View File

@@ -0,0 +1,20 @@
version: "3.8"
services:
n8n:
image: docker.n8n.io/n8nio/n8n:latest
container_name: n8n-ai
restart: unless-stopped
ports:
- "${N8N_PORT:-5678}:5678"
volumes:
- n8n_data:/home/node/.n8n
environment:
- N8N_BASIC_AUTH_ACTIVE=${N8N_AUTH:-true}
- N8N_BASIC_AUTH_USER=${N8N_USER:-admin}
- N8N_BASIC_AUTH_PASSWORD=${N8N_PASSWORD:-changeme}
- WEBHOOK_URL=${WEBHOOK_URL:-http://localhost:5678/}
- N8N_AI_ENABLED=true
volumes:
n8n_data:

36
ai-templates-0/stacks/nvidia-nim/docker-compose.yml Normal file
View File

@@ -0,0 +1,36 @@
version: "3.8"
services:
nim:
image: nvcr.io/nim/${NIM_MODEL:-meta/llama-3.1-8b-instruct}:${NIM_VERSION:-latest}
container_name: nvidia-nim
restart: unless-stopped
ports:
- "${NIM_PORT:-8000}:8000"
volumes:
- nim_cache:/opt/nim/.cache
environment:
- NGC_API_KEY=${NGC_API_KEY}
- NIM_MAX_MODEL_LEN=${MAX_MODEL_LEN:-4096}
- NIM_GPU_MEMORY_UTILIZATION=${GPU_MEM_UTIL:-0.9}
- NIM_MAX_BATCH_SIZE=${MAX_BATCH:-256}
- NIM_LOG_LEVEL=${LOG_LEVEL:-INFO}
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
shm_size: ${SHM_SIZE:-16g}
ulimits:
memlock: -1
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:8000/v1/health/ready"]
interval: 30s
timeout: 10s
retries: 10
start_period: 120s
volumes:
nim_cache:

25
ai-templates-0/stacks/ollama/docker-compose.yml Normal file
View File

@@ -0,0 +1,25 @@
version: "3.8"
services:
ollama:
image: ollama/ollama:latest
container_name: ollama
restart: unless-stopped
ports:
- "${OLLAMA_PORT:-11434}:11434"
volumes:
- ollama_data:/root/.ollama
environment:
- OLLAMA_HOST=0.0.0.0
- OLLAMA_NUM_PARALLEL=${OLLAMA_NUM_PARALLEL:-4}
- OLLAMA_MAX_LOADED_MODELS=${OLLAMA_MAX_LOADED_MODELS:-2}
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
volumes:
ollama_data:

57
ai-templates-0/stacks/onnx-runtime/docker-compose.yml Normal file
View File

@@ -0,0 +1,57 @@
version: "3.8"
services:
# GPU variant — for data center / cloud nodes
onnx-runtime-gpu:
image: mcr.microsoft.com/onnxruntime/server:latest
container_name: onnx-runtime-gpu
restart: unless-stopped
profiles: ["gpu"]
ports:
- "${HTTP_PORT:-8001}:8001"
- "${GRPC_PORT:-50051}:50051"
volumes:
- onnx_models:/models
environment:
- ORT_LOG_LEVEL=${LOG_LEVEL:-WARNING}
command: >
--model_path /models/${MODEL_FILE:-model.onnx}
--http_port 8001
--grpc_port 50051
--num_threads ${NUM_THREADS:-4}
--execution_provider ${EXEC_PROVIDER:-cuda}
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: 1
capabilities: [gpu]
# CPU variant — for edge nodes, ARM, resource-constrained environments
onnx-runtime-cpu:
image: mcr.microsoft.com/onnxruntime/server:latest
container_name: onnx-runtime-cpu
restart: unless-stopped
profiles: ["cpu", "edge"]
ports:
- "${HTTP_PORT:-8001}:8001"
- "${GRPC_PORT:-50051}:50051"
volumes:
- onnx_models:/models
environment:
- ORT_LOG_LEVEL=${LOG_LEVEL:-WARNING}
command: >
--model_path /models/${MODEL_FILE:-model.onnx}
--http_port 8001
--grpc_port 50051
--num_threads ${NUM_THREADS:-4}
--execution_provider cpu
deploy:
resources:
limits:
cpus: "${CPU_LIMIT:-2.0}"
memory: ${MEM_LIMIT:-2G}
volumes:
onnx_models:

39
ai-templates-0/stacks/open-webui/docker-compose.yml Normal file
View File

@@ -0,0 +1,39 @@
version: "3.8"
services:
open-webui:
image: ghcr.io/open-webui/open-webui:main
container_name: open-webui
restart: unless-stopped
ports:
- "${OPEN_WEBUI_PORT:-3000}:8080"
volumes:
- open_webui_data:/app/backend/data
environment:
- OLLAMA_BASE_URL=${OLLAMA_BASE_URL:-http://ollama:11434}
- WEBUI_SECRET_KEY=${WEBUI_SECRET_KEY:-changeme}
- ENABLE_SIGNUP=${ENABLE_SIGNUP:-true}
depends_on:
- ollama
ollama:
image: ollama/ollama:latest
container_name: ollama
restart: unless-stopped
ports:
- "${OLLAMA_PORT:-11434}:11434"
volumes:
- ollama_data:/root/.ollama
environment:
- OLLAMA_HOST=0.0.0.0
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
volumes:
open_webui_data:
ollama_data:

55
ai-templates-0/stacks/prefect/docker-compose.yml Normal file
View File

@@ -0,0 +1,55 @@
version: "3.8"
services:
prefect-server:
image: prefecthq/prefect:${PREFECT_VERSION:-3-latest}
container_name: prefect-server
restart: unless-stopped
ports:
- "${PREFECT_PORT:-4200}:4200"
volumes:
- prefect_data:/root/.prefect
- prefect_flows:/flows
environment:
- PREFECT_SERVER_API_HOST=0.0.0.0
- PREFECT_SERVER_API_PORT=4200
- PREFECT_API_DATABASE_CONNECTION_URL=postgresql+asyncpg://${PG_USER:-prefect}:${PG_PASSWORD:-prefect}@prefect-db:5432/${PG_DB:-prefect}
- PREFECT_SERVER_ANALYTICS_ENABLED=${ANALYTICS:-false}
command: prefect server start
depends_on:
prefect-db:
condition: service_healthy
prefect-worker:
image: prefecthq/prefect:${PREFECT_VERSION:-3-latest}
container_name: prefect-worker
restart: unless-stopped
volumes:
- prefect_flows:/flows
- /var/run/docker.sock:/var/run/docker.sock
environment:
- PREFECT_API_URL=http://prefect-server:4200/api
command: prefect worker start --pool default-agent-pool --type docker
depends_on:
- prefect-server
prefect-db:
image: postgres:16-alpine
container_name: prefect-db
restart: unless-stopped
environment:
- POSTGRES_USER=${PG_USER:-prefect}
- POSTGRES_PASSWORD=${PG_PASSWORD:-prefect}
- POSTGRES_DB=${PG_DB:-prefect}
volumes:
- prefect_pg_data:/var/lib/postgresql/data
healthcheck:
test: ["CMD-SHELL", "pg_isready -U ${PG_USER:-prefect}"]
interval: 10s
timeout: 5s
retries: 5
volumes:
prefect_data:
prefect_flows:
prefect_pg_data:

19
ai-templates-0/stacks/qdrant/docker-compose.yml Normal file
View File

@@ -0,0 +1,19 @@
version: "3.8"
services:
qdrant:
image: qdrant/qdrant:latest
container_name: qdrant
restart: unless-stopped
ports:
- "${QDRANT_HTTP_PORT:-6333}:6333"
- "${QDRANT_GRPC_PORT:-6334}:6334"
volumes:
- qdrant_data:/qdrant/storage
- qdrant_snapshots:/qdrant/snapshots
environment:
- QDRANT__SERVICE__API_KEY=${QDRANT_API_KEY:-}
volumes:
qdrant_data:
qdrant_snapshots:

60
ai-templates-0/stacks/ray-cluster/docker-compose.yml Normal file
View File

@@ -0,0 +1,60 @@
version: "3.8"
services:
ray-head:
image: rayproject/ray-ml:${RAY_VERSION:-2.40.0}-py310-gpu
container_name: ray-head
restart: unless-stopped
ports:
- "${DASHBOARD_PORT:-8265}:8265"
- "${CLIENT_PORT:-10001}:10001"
- "${GCS_PORT:-6379}:6379"
- "${SERVE_PORT:-8000}:8000"
volumes:
- ray_data:/home/ray/data
- ray_results:/home/ray/ray_results
command: >
ray start --head
--port=6379
--dashboard-host=0.0.0.0
--dashboard-port=8265
--num-gpus=${HEAD_GPUS:-1}
--block
environment:
- RAY_GRAFANA_HOST=http://grafana:3000
- RAY_PROMETHEUS_HOST=http://prometheus:9090
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
shm_size: ${SHM_SIZE:-8g}
ray-worker:
image: rayproject/ray-ml:${RAY_VERSION:-2.40.0}-py310-gpu
restart: unless-stopped
depends_on:
- ray-head
command: >
ray start
--address=ray-head:6379
--num-gpus=${WORKER_GPUS:-1}
--num-cpus=${WORKER_CPUS:-4}
--block
volumes:
- ray_data:/home/ray/data
deploy:
replicas: ${NUM_WORKERS:-1}
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
shm_size: ${SHM_SIZE:-8g}
volumes:
ray_data:
ray_results:

25
ai-templates-0/stacks/stable-diffusion-webui/docker-compose.yml Normal file
View File

@@ -0,0 +1,25 @@
version: "3.8"
services:
stable-diffusion-webui:
image: universonic/stable-diffusion-webui:latest
container_name: stable-diffusion-webui
restart: unless-stopped
ports:
- "${SD_PORT:-7860}:7860"
volumes:
- sd_data:/data
- sd_output:/output
environment:
- CLI_ARGS=${CLI_ARGS:---listen --api --xformers}
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
volumes:
sd_data:
sd_output:

35
ai-templates-0/stacks/text-generation-webui/docker-compose.yml Normal file
View File

@@ -0,0 +1,35 @@
version: "3.8"
services:
text-gen-webui:
image: atinoda/text-generation-webui:default-nvidia
container_name: text-generation-webui
restart: unless-stopped
ports:
- "${WEBUI_PORT:-7860}:7860"
- "${API_PORT:-5000}:5000"
- "${STREAM_PORT:-5005}:5005"
volumes:
- tgw_characters:/app/characters
- tgw_loras:/app/loras
- tgw_models:/app/models
- tgw_presets:/app/presets
- tgw_prompts:/app/prompts
- tgw_extensions:/app/extensions
environment:
- EXTRA_LAUNCH_ARGS=${EXTRA_LAUNCH_ARGS:---listen --api}
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
volumes:
tgw_characters:
tgw_loras:
tgw_models:
tgw_presets:
tgw_prompts:
tgw_extensions:

43
ai-templates-0/stacks/triton/docker-compose.yml Normal file
View File

@@ -0,0 +1,43 @@
version: "3.8"
services:
triton:
image: nvcr.io/nvidia/tritonserver:${TRITON_VERSION:-24.08}-py3
container_name: triton-inference-server
restart: unless-stopped
ports:
- "${HTTP_PORT:-8000}:8000"
- "${GRPC_PORT:-8001}:8001"
- "${METRICS_PORT:-8002}:8002"
volumes:
- triton_models:/models
command: >
tritonserver
--model-repository=/models
--strict-model-config=${STRICT_CONFIG:-false}
--log-verbose=${LOG_VERBOSE:-0}
--exit-on-error=${EXIT_ON_ERROR:-false}
--rate-limit=${RATE_LIMIT:-off}
--model-control-mode=${MODEL_CONTROL:-poll}
--repository-poll-secs=${POLL_INTERVAL:-30}
environment:
- CUDA_VISIBLE_DEVICES=${CUDA_DEVICES:-all}
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
shm_size: ${SHM_SIZE:-1g}
ulimits:
memlock: -1
stack: 67108864
healthcheck:
test: ["CMD", "curl", "-f", "http://localhost:8000/v2/health/ready"]
interval: 30s
timeout: 10s
retries: 5
volumes:
triton_models:

29
ai-templates-0/stacks/vllm/docker-compose.yml Normal file
View File

@@ -0,0 +1,29 @@
version: "3.8"
services:
vllm:
image: vllm/vllm-openai:latest
container_name: vllm
restart: unless-stopped
ports:
- "${VLLM_PORT:-8000}:8000"
volumes:
- vllm_cache:/root/.cache/huggingface
environment:
- HUGGING_FACE_HUB_TOKEN=${HF_TOKEN:-}
command: >
--model ${MODEL_NAME:-meta-llama/Llama-3.1-8B-Instruct}
--max-model-len ${MAX_MODEL_LEN:-4096}
--gpu-memory-utilization ${GPU_MEM_UTIL:-0.90}
--tensor-parallel-size ${TENSOR_PARALLEL:-1}
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]
ipc: host
volumes:
vllm_cache:

22
ai-templates-0/stacks/weaviate/docker-compose.yml Normal file
View File

@@ -0,0 +1,22 @@
version: "3.8"
services:
weaviate:
image: cr.weaviate.io/semitechnologies/weaviate:latest
container_name: weaviate
restart: unless-stopped
ports:
- "${WEAVIATE_HTTP_PORT:-8080}:8080"
- "${WEAVIATE_GRPC_PORT:-50051}:50051"
volumes:
- weaviate_data:/var/lib/weaviate
environment:
- QUERY_DEFAULTS_LIMIT=25
- AUTHENTICATION_ANONYMOUS_ACCESS_ENABLED=${ANON_ACCESS:-true}
- PERSISTENCE_DATA_PATH=/var/lib/weaviate
- DEFAULT_VECTORIZER_MODULE=${VECTORIZER:-none}
- CLUSTER_HOSTNAME=node1
- ENABLE_MODULES=${MODULES:-text2vec-transformers,generative-openai}
volumes:
weaviate_data:

19
ai-templates-0/stacks/whisper/docker-compose.yml Normal file
View File

@@ -0,0 +1,19 @@
version: "3.8"
services:
whisper:
image: onerahmet/openai-whisper-asr-webservice:latest-gpu
container_name: whisper-asr
restart: unless-stopped
ports:
- "${WHISPER_PORT:-9000}:9000"
environment:
- ASR_MODEL=${ASR_MODEL:-base}
- ASR_ENGINE=${ASR_ENGINE:-openai_whisper}
deploy:
resources:
reservations:
devices:
- driver: nvidia
count: all
capabilities: [gpu]