Ashwin Bharambe 6f4f51f8d9 apply anti affinity and separate PVCs for the models so the two vllms can be mapped to two nodes and avoid causing unnecessary memory pressure		2025-06-01 16:54:36 -07:00
..
apply.sh	split off safety so it can be applied one at a time	2025-06-01 15:59:00 -07:00
chroma-k8s.yaml.template	split off safety so it can be applied one at a time	2025-06-01 15:59:00 -07:00
postgres-k8s.yaml.template	docs(kubernetes): add a more fleshed out example of a Demo Kubernetes cluster	2025-06-01 14:25:54 -07:00
stack-configmap.yaml	docs(kubernetes): add a more fleshed out example of a Demo Kubernetes cluster	2025-06-01 14:25:54 -07:00
stack-k8s.yaml.template	split off safety so it can be applied one at a time	2025-06-01 15:59:00 -07:00
stack_run_config.yaml	docs(kubernetes): add a more fleshed out example of a Demo Kubernetes cluster	2025-06-01 14:25:54 -07:00
vllm-k8s.yaml.template	apply anti affinity and separate PVCs for the models so the two vllms can be mapped to two nodes and avoid causing unnecessary memory pressure	2025-06-01 16:54:36 -07:00
vllm-safety-k8s.yaml.template	apply anti affinity and separate PVCs for the models so the two vllms can be mapped to two nodes and avoid causing unnecessary memory pressure	2025-06-01 16:54:36 -07:00