Deploy GPU-optimized generative AI models using the MAX container Helm chart for Kubernetes.
434
Use the MAX container Helm chart to pull the MAX container image, download model weights, and configure and launch the specified model as an endpoint.
For more information on container contents and instance compatibility, see MAX container in the MAX documentation.
You can install the MAX container Helm chart with the following command:
helm install max-openai-api oci://registry-1.docker.io/modular/max-openai-api-chart \
--version 24.6.0 \
--namespace max-openai-api-demo \
--set huggingfaceRepoId=<model-provider/model-id> \
--set maxServe.maxLength=512 \
--set maxServe.maxCacheBatchSize=16 \
--set env.HF_HUB_ENABLE_HF_TRANSFER=1 \
--timeout 15m0s \
--wait
Supported tags are updated to the latest MAX versions, which includes the latest stable release.
Stable
For more information on Modular and its products, visit the Modular documentation site.
To stay up to date with new releases, sign up for our newsletter, check out the community, and join our forum.
If you're interested in becoming a design partner to get early access and give us feedback, please contact us.
![]()
Content type
Helm
Digest
sha256:8333c3bcb…
Size
7.9 kB
Last updated
over 1 year ago
helm pull oci://registry-1.docker.io/modular/max-openai-api-chart --version 24.6.0Pulls:
24
Last week