Cleaning distributed inference with ray related artifacts.

Author: dkennetzoracle

docs/api_documentation/README.md

@@ -10,7 +10,7 @@
 | -------------------------------------------- | ------- | -------- | --------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | recipe_id                                    | string  | Yes      | One of the following: `llm_inference_nvidia`, `lora_finetune_nvidia`, or `mlcommons_lora_finetune_nvidia`                                                                                                                                                                                                                                                                         |
 | deployment_name                              | string  | Yes      | Any deployment name to identify the deployment details easily. Must be unique from other recipe deployments.                                                                                                                                                                                                                                                                      |
-| recipe_mode                                  | string  | Yes      | One of the following: `service`, `job`, `update`, `shared_node_pool` or `raycluster`. Enter `service` for inference recipe deployments, `job` for fine-tuning recipe deployments, `update` for updating existing deployments (currently only supported for MIG), `shared_node_pool` for creating a shared node pool, and `raycluster` when doing multinode inference deployments. |
+| recipe_mode                                  | string  | Yes      | One of the following: `service`, `job`, `update`, or `shared_node_pool`. Enter `service` for inference recipe deployments, `job` for fine-tuning recipe deployments, `update` for updating existing deployments (currently only supported for MIG), and `shared_node_pool` for creating a shared node pool. |
 | recipe_node_labels                           | object  | No       | Additional labels to apply to a node pool in the form `{"label": "value"}`                                                                                                                                                                                                                                                                                                        |
 | service_endpoint_domain                      | string  | No       | Required for inference recipe deployments. Inference endpoint will point to this domain.                                                                                                                                                                                                                                                                                          |
 | recipe_max_pods_per_node                     | int     | No       | Allow a node to schedule more pods than default 31 from kubernetes. Required for certain MIG configurations which can slice up to 56 times.                                                                                                                                                                                                                                       |

docs/custom_blueprints/blueprint_json_schema.json

@@ -43,8 +43,7 @@
               "service",
               "job",
               "update",
-              "shared_node_pool",
-              "raycluster"
+              "shared_node_pool"
             ]
           },
           "recipe_replica_count": {
@@ -411,66 +410,6 @@
           },
           "skip_quota_validation": {
             "type": "boolean"
-          },
-          "recipe_raycluster_params": {
-            "type": "object",
-            "properties": {
-              "head_node_num_cpus": {
-                "type": "integer"
-              },
-              "head_node_num_gpus": {
-                "type": "integer"
-              },
-              "head_node_cpu_mem_in_gbs": {
-                "type": "integer"
-              },
-              "num_worker_nodes": {
-                "type": "integer"
-              },
-              "worker_node_num_cpus": {
-                "type": "integer"
-              },
-              "worker_node_num_gpus": {
-                "type": "integer"
-              },
-              "worker_node_cpu_mem_in_gbs": {
-                "type": "integer"
-              },
-              "model_path_in_container": {
-                "type": "string"
-              },
-              "redis_port": {
-                "type": "integer"
-              },
-              "dashboard_port": {
-                "type": "integer"
-              },
-              "metrics_export_port": {
-                "type": "integer"
-              },
-              "rayclient_server_port": {
-                "type": "integer"
-              },
-              "worker_image_uri": {
-                "type": "string"
-              },
-              "head_image_uri": {
-                "type": "string"
-              },
-              "rayjob_image_uri": {
-                "type": "string"
-              }
-            },
-            "additionalProperties": false,
-            "required": [
-              "head_node_num_cpus",
-              "head_node_num_gpus",
-              "head_node_cpu_mem_in_gbs",
-              "num_worker_nodes",
-              "worker_node_num_cpus",
-              "worker_node_num_gpus",
-              "worker_node_cpu_mem_in_gbs"
-            ]
           }
         },
         "required": ["recipe_mode", "deployment_name"],