Add GPU to ClusterConfiguration

Author: oksanabaza

demo-notebooks/additional-demos/hf_interactive.ipynb

@@ -93,12 +93,13 @@
     "# The SDK will try to find the name of your default local queue based on the annotation \"kueue.x-k8s.io/default-queue\": \"true\" unless you specify the local queue manually below\n",
     "cluster = Cluster(ClusterConfiguration(name='hfgputest', \n",
     "                                       namespace=\"default\", # Update to your namespace\n",
+    "                                       head_gpus=1, # For GPU enabled workloads set the head_gpus and num_gpus\n",
+    "                                       num_gpus=1,\n",
     "                                       num_workers=1,\n",
     "                                       min_cpus=8, \n",
     "                                       max_cpus=8, \n",
     "                                       min_memory=16, \n",
     "                                       max_memory=16, \n",
-    "                                       num_gpus=4,\n",
     "                                       image=\"quay.io/project-codeflare/ray:latest-py39-cu118\",\n",
     "                                       write_to_file=False, # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources \n",
     "                                       # local_queue=\"local-queue-name\" # Specify the local queue manually\n",

demo-notebooks/additional-demos/local_interactive.ipynb

@@ -55,12 +55,13 @@
     "\n",
     "cluster = Cluster(ClusterConfiguration(namespace=namespace,\n",
     "                                       name=cluster_name,\n",
+    "                                       head_gpus=0, # For GPU enabled workloads set the head_gpus and num_gpus\n",
+    "                                       num_gpus=0,\n",
     "                                       num_workers=1,\n",
     "                                       min_cpus=1,\n",
     "                                       max_cpus=1,\n",
     "                                       min_memory=4,\n",
     "                                       max_memory=4,\n",
-    "                                       num_gpus=0,\n",
     "                                       image=\"quay.io/project-codeflare/ray:latest-py39-cu118\",\n",
     "                                       write_to_file=False, # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources \n",
     "                                       # local_queue=\"local-queue-name\" # Specify the local queue manually\n",

demo-notebooks/additional-demos/ray_job_client.ipynb

@@ -46,12 +46,13 @@
     "cluster = Cluster(ClusterConfiguration(\n",
     "    name='jobtest',\n",
     "    namespace='default', # Update to your namespace\n",
+    "    head_gpus=0, # For GPU enabled workloads set the head_gpus and num_gpus\n",
+    "    num_gpus=0,\n",
     "    num_workers=2,\n",
     "    min_cpus=1,\n",
     "    max_cpus=1,\n",
     "    min_memory=4,\n",
     "    max_memory=4,\n",
-    "    num_gpus=0,\n",
     "    image=\"quay.io/project-codeflare/ray:latest-py39-cu118\",\n",
     "    write_to_file=False # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources \n",
     "))"

demo-notebooks/guided-demos/0_basic_ray.ipynb

@@ -61,14 +61,15 @@
     "# Create and configure our cluster object\n",
     "# The SDK will try to find the name of your default local queue based on the annotation \"kueue.x-k8s.io/default-queue\": \"true\" unless you specify the local queue manually below\n",
     "cluster = Cluster(ClusterConfiguration(\n",
-    "    name='raytest',\n",
+    "    name='raytest', \n",
     "    namespace='default', # Update to your namespace\n",
+    "    head_gpus=0, # For GPU enabled workloads set the head_gpus and num_gpus\n",
+    "    num_gpus=0,\n",
     "    num_workers=2,\n",
     "    min_cpus=1,\n",
     "    max_cpus=1,\n",
     "    min_memory=4,\n",
     "    max_memory=4,\n",
-    "    num_gpus=0,\n",
     "    image=\"quay.io/project-codeflare/ray:latest-py39-cu118\",\n",
     "    write_to_file=False, # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources \n",
     "    # local_queue=\"local-queue-name\" # Specify the local queue manually\n",

demo-notebooks/guided-demos/1_cluster_job_client.ipynb

@@ -45,13 +45,13 @@
     "cluster = Cluster(ClusterConfiguration(\n",
     "    name='jobtest',\n",
     "    namespace='default', # Update to your namespace\n",
+    "    head_gpus=1, # For GPU enabled workloads set the head_gpus and num_gpus\n",
+    "    num_gpus=1,\n",
     "    num_workers=2,\n",
     "    min_cpus=1,\n",
     "    max_cpus=1,\n",
     "    min_memory=4,\n",
     "    max_memory=4,\n",
-    "    num_gpus=1,\n",
-    "    head_gpus=1,\n",
     "    image=\"quay.io/project-codeflare/ray:latest-py39-cu118\",\n",
     "    write_to_file=False, # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources \n",
     "    # local_queue=\"local-queue-name\" # Specify the local queue manually\n",

demo-notebooks/guided-demos/2_basic_interactive.ipynb

@@ -62,12 +62,13 @@
     "cluster = Cluster(ClusterConfiguration(\n",
     "    name=cluster_name,\n",
     "    namespace=namespace,\n",
+    "    head_gpus=1, # For GPU enabled workloads set the head_gpus and num_gpus\n",
+    "    num_gpus=1,\n",
     "    num_workers=2,\n",
     "    min_cpus=2,\n",
     "    max_cpus=2,\n",
     "    min_memory=8,\n",
     "    max_memory=8,\n",
-    "    num_gpus=1,\n",
     "    image=\"quay.io/project-codeflare/ray:latest-py39-cu118\",\n",
     "    write_to_file=False, # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources \n",
     "    # local_queue=\"local-queue-name\" # Specify the local queue manually\n",

demo-notebooks/guided-demos/notebook-ex-outputs/0_basic_ray.ipynb

@@ -71,12 +71,13 @@
     "cluster = Cluster(ClusterConfiguration(\n",
     "    name='raytest',\n",
     "    namespace='default', # Update to your namespace\n",
+    "    head_gpus=0, # For GPU enabled workloads set the head_gpus and num_gpus\n",
+    "    num_gpus=0,\n",
     "    num_workers=2,\n",
     "    min_cpus=1,\n",
     "    max_cpus=1,\n",
     "    min_memory=4,\n",
     "    max_memory=4,\n",
-    "    num_gpus=0,\n",
     "    image=\"quay.io/project-codeflare/ray:latest-py39-cu118\",\n",
     "    write_to_file=False, # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources \n",
     "    # local_queue=\"local-queue-name\" # Specify the local queue manually\n",

demo-notebooks/guided-demos/notebook-ex-outputs/1_cluster_job_client.ipynb

@@ -45,13 +45,13 @@
     "cluster = Cluster(ClusterConfiguration(\n",
     "    name='jobtest',\n",
     "    namespace='default', # Update to your namespace\n",
+    "    head_gpus=1, # For GPU enabled workloads set the head_gpus and num_gpus\n",
+    "    num_gpus=1,\n",
     "    num_workers=2,\n",
     "    min_cpus=1,\n",
     "    max_cpus=1,\n",
     "    min_memory=4,\n",
     "    max_memory=4,\n",
-    "    num_gpus=1,\n",
-    "    head_gpus=1,\n",
     "    image=\"quay.io/project-codeflare/ray:latest-py39-cu118\",\n",
     "    write_to_file=False, # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources \n",
     "    # local_queue=\"local-queue-name\" # Specify the local queue manually\n",

demo-notebooks/guided-demos/notebook-ex-outputs/2_basic_interactive.ipynb

@@ -70,12 +70,13 @@
     "cluster = Cluster(ClusterConfiguration(\n",
     "    name=cluster_name,\n",
     "    namespace=namespace,\n",
+    "    head_gpus=1, # For GPU enabled workloads set the head_gpus and num_gpus\n",
+    "    num_gpus=1,\n",
     "    num_workers=2,\n",
     "    min_cpus=2,\n",
     "    max_cpus=2,\n",
     "    min_memory=8,\n",
     "    max_memory=8,\n",
-    "    num_gpus=1,\n",
     "    image=\"quay.io/project-codeflare/ray:latest-py39-cu118\",\n",
     "    write_to_file=False, # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources \n",
     "    # local_queue=\"local-queue-name\" # Specify the local queue manually\n",

demo-notebooks/guided-demos/preview_nbs/0_basic_ray.ipynb

@@ -63,12 +63,13 @@
     "cluster = Cluster(ClusterConfiguration(\n",
     "    name='raytest',\n",
     "    namespace='default', # Update to your namespace\n",
+    "    head_gpus=0, # For GPU enabled workloads set the head_gpus and num_gpus\n",
+    "    num_gpus=0,\n",
     "    num_workers=2,\n",
     "    min_cpus=1,\n",
     "    max_cpus=1,\n",
     "    min_memory=4,\n",
     "    max_memory=4,\n",
-    "    num_gpus=0,\n",
     "    image=\"quay.io/project-codeflare/ray:latest-py39-cu118\",\n",
     "    write_to_file=False, # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources \n",
     "    # local_queue=\"local-queue-name\" # Specify the local queue manually\n",

demo-notebooks/guided-demos/preview_nbs/1_cluster_job_client.ipynb

@@ -45,13 +45,13 @@
     "cluster = Cluster(ClusterConfiguration(\n",
     "    name='jobtest',\n",
     "    namespace='default', # Update to your namespace\n",
+    "    head_gpus=1, # For GPU enabled workloads set the head_gpus and num_gpus\n",
+    "    num_gpus=1,\n",
     "    num_workers=2,\n",
     "    min_cpus=1,\n",
     "    max_cpus=1,\n",
     "    min_memory=4,\n",
     "    max_memory=4,\n",
-    "    num_gpus=1,\n",
-    "    head_gpus=1,\n",
     "    image=\"quay.io/project-codeflare/ray:latest-py39-cu118\",\n",
     "    write_to_file=False, # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources\n",
     "    # local_queue=\"local-queue-name\" # Specify the local queue manually\n",

demo-notebooks/guided-demos/preview_nbs/2_basic_interactive.ipynb

@@ -62,12 +62,13 @@
     "cluster = Cluster(ClusterConfiguration(\n",
     "    name=cluster_name,\n",
     "    namespace=namespace,\n",
+    "    head_gpus=1, # For GPU enabled workloads set the head_gpus and num_gpus\n",
+    "    num_gpus=1,\n",
     "    num_workers=2,\n",
     "    min_cpus=2,\n",
     "    max_cpus=2,\n",
     "    min_memory=8,\n",
     "    max_memory=8,\n",
-    "    num_gpus=1,\n",
     "    image=\"quay.io/project-codeflare/ray:latest-py39-cu118\",\n",
     "    write_to_file=False, # When enabled Ray Cluster yaml files are written to /HOME/.codeflare/resources \n",
     "    # local_queue=\"local-queue-name\" # Specify the local queue manually\n",

docs/cluster-configuration.md

@@ -12,12 +12,12 @@ cluster = Cluster(ClusterConfiguration(
     head_cpus=1, # Default 2
     head_memory=1, # Default 8
     head_gpus=0, # Default 0
+    num_gpus=0, # Default 0
     num_workers=1, # Default 1
     min_cpus=1, # Default 1
     max_cpus=1, # Default 1
     min_memory=2, # Default 2
     max_memory=2, # Default 2
-    num_gpus=0, # Default 0
     mcad=True, # Default True
     image="quay.io/project-codeflare/ray:latest-py39-cu118", # Mandatory Field
     machine_types=["m5.xlarge", "g4dn.xlarge"],