Charts
3 chartsMachine learning & AI charts
Hardened Helm charts in the machine learning & ai category. Each deploys our hardened image pinned by its signed digest, with production defaults.
0 CVEmlflow
MLflow Tracking Server for the ML lifecycle — experiment tracking, model registry, and run metadata over a REST/UI on port 5000. Packaged as the lightweight mlflow-skinny stack (gunicorn + psycopg2 + boto3) on a hardened Wolfi python base; needs an external PostgreSQL backend store and an artifact store (S3 or PVC).
chart v · app v3.14.0
Machine learning & AIstandardApache-2.0- 0 CVE
ollama
Local LLM runtime that pulls, runs, and serves open models (Llama, Gemma, Qwen, DeepSeek, and more) behind a simple REST API. CPU-only image; the chart mounts a writable volume for the model store.
chart v · app v0.32.5
Machine learning & AIstandardMIT - 0 CVE
vllm
vLLM, the high-throughput LLM inference and serving engine with an OpenAI-compatible API. CPU build — installs vLLM's prebuilt CPU wheel (torch+cpu, no source compile, no CUDA) into a venv on a hardened Wolfi python-3.12 base, 0-CVE across ~140 Python packages. The user supplies the model; the chart runs it as a StatefulSet with a persistent model cache.
chart v · app v0.24.0
Machine learning & AIstandardApache-2.0