v1.0.4

What's Changed

• fix: Update cleanup script by @ratnopamc in #595
• fix: Update karpenter version for trainium-inferentia blueprint by @ratnopamc in #599
• docs: Add video link for Deploy accelerator-agnostic inference pipelines to Amazon EKS by @TalHibner in #600
• feat: Replaced NIM architecture diagram with self-made NIM on EKS arch diagram by @hustshawn in #612
• feat: RayServe with vLLM using AWS Neuron on Amazon EKS by @ratnopamc in #607
• feat: Mountpoint S3 for loading additional Spark Jars by @bainskb in #606
• feat: Support preloading container images into Bottlerocket data volumes with Karpenter by @lindarr915 in #587
• chore: Delete ai-ml/kubeflow directory by @askulkarni2 in #619
• feat: Updated mountpoint-s3 for spark readme by @bainskb in #618
• feat: Trainium blueprint upgrade and Llama3.1 405b Distributed inference example by @vara-bonthu in #622
• feat: Neuron scheduler update for trainium-inferentia blueprints by @ratnopamc in #624
• feat: Website Updates by @vara-bonthu in #626
• feat: Updates to the sidebar by @vara-bonthu in #627
• feat: Added deprecating notes; added Jark stack doc;added warnings for ML p… by @vara-bonthu in #628
• feat: NVIDIA NIM Updates by @vara-bonthu in #631
• feat: Udate NVIDIA NIM blueprint with grafana dashboard and docs by @ratnopamc in #633
• feat: Add OpenWebUI for vllm-rayserve-inf2 blueprint by @ratnopamc in #635
• feat: Updated EMR on EKS Blueprint by @vara-bonthu in #638
• chore: Update PULL_REQUEST_TEMPLATE.md by @askulkarni2 in #643
• chore: Add access entry for workshop by @askulkarni2 in #644
• fix: Use eks module for access_entries for trn-inf blueprint by @askulkarni2 in #646
• chore(deps): bump send and express in /website by @dependabot in #653
• chore(deps): bump serve-static and express in /website by @dependabot in #652
• feat: Updates to the llama3.1 405 model scripts by @vara-bonthu in #655
• feat: Add cloudwatch eks add on with enhanced monitoring for neuron by @ratnopamc in #651
• chore: Update cmd-shell image to python3.11 by @askulkarni2 in #656
• docs: Website documentation for vllm inferencing using rayserve on AWS Inferentia by @sindhupalakodety in #637
• feat: Adding support for AWS Batch by @delagoya in #620
• docs: Ray vLLM Inf2 website doc updates by @ratnopamc in #657
• feat: Observability for RayServe and vLLM GPU by @shivam-dubey-1 in #642
• feat: Add binpacking examples by @hitsub2 in #615
• feat: Spark K8s Operator on EKS IPv6 cluster by @ovaleanu in #499

New Contributors

• @TalHibner made their first contribution in #600
• @bainskb made their first contribution in #606
• @sindhupalakodety made their first contribution in #637
• @delagoya made their first contribution in #620
• @shivam-dubey-1 made their first contribution in #642

Full Changelog: v1.0.3...v1.0.4