Skip to content

Cleaning distributed inference with ray related artifacts. #53

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 1 commit into from
May 12, 2025
Merged

Cleaning distributed inference with ray related artifacts. #53

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
2 changes: 1 addition & 1 deletion docs/api_documentation/README.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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. |
Expand Down
63 changes: 1 addition & 62 deletions docs/custom_blueprints/blueprint_json_schema.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -43,8 +43,7 @@
"service",
"job",
"update",
"shared_node_pool",
"raycluster"
"shared_node_pool"
]
},
"recipe_replica_count": {
Expand Down Expand Up @@ -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"],
Expand Down