Update notebooks and docs with updated Cluster Configuration args

project-codeflare · Aug 22, 2024 · 95b2165 · 95b2165
1 parent ee307a9
commit 95b2165
Show file tree

Hide file tree

Showing 13 changed files with 79 additions and 80 deletions.
diff --git a/demo-notebooks/additional-demos/hf_interactive.ipynb b/demo-notebooks/additional-demos/hf_interactive.ipynb
@@ -91,13 +91,13 @@
     "# 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_name= \"hfgputest\"\n",
     "cluster = Cluster(ClusterConfiguration(name=cluster_name, \n",
-    "                                       head_gpus=1, # For GPU enabled workloads set the head_gpus and num_gpus\n",
-    "                                       num_gpus=1,\n",
+    "                                       head_extended_resource_requests={'nvidia.com/gpu':1}, # For GPU enabled workloads set the head_extended_resource_requests and worker_extended_resource_requests\n",
+    "                                       worker_extended_resource_requests={'nvidia.com/gpu':1},\n",
     "                                       num_workers=1,\n",
-    "                                       min_cpus=8, \n",
-    "                                       max_cpus=8, \n",
-    "                                       min_memory=16, \n",
-    "                                       max_memory=16, \n",
+    "                                       worker_cpu_requests=8, \n",
+    "                                       worker_cpu_limits=8, \n",
+    "                                       worker_memory_requests=16, \n",
+    "                                       worker_memory_limits=16, \n",
     "                                       # image=\"\", # Optional Field \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",

diff --git a/demo-notebooks/additional-demos/local_interactive.ipynb b/demo-notebooks/additional-demos/local_interactive.ipynb
@@ -54,13 +54,13 @@
     "\n",
     "cluster = Cluster(ClusterConfiguration(\n",
     "                                       name=cluster_name,\n",
-    "                                       head_gpus=0, # For GPU enabled workloads set the head_gpus and num_gpus\n",
-    "                                       num_gpus=0,\n",
+    "                                       head_extended_resource_requests={'nvidia.com/gpu':0}, # For GPU enabled workloads set the head_extended_resource_requests and worker_extended_resource_requests\n",
+    "                                       worker_extended_resource_requests={'nvidia.com/gpu':0},\n",
     "                                       num_workers=1,\n",
-    "                                       min_cpus=1,\n",
-    "                                       max_cpus=1,\n",
-    "                                       min_memory=4,\n",
-    "                                       max_memory=4,\n",
+    "                                       worker_cpu_requests=1,\n",
+    "                                       worker_cpu_limits=1,\n",
+    "                                       worker_memory_requests=4,\n",
+    "                                       worker_memory_limits=4,\n",
     "                                       # image=\"\", # Optional Field \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",

diff --git a/demo-notebooks/additional-demos/ray_job_client.ipynb b/demo-notebooks/additional-demos/ray_job_client.ipynb
@@ -55,13 +55,13 @@
     "# 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(\n",
     "    name='jobtest',\n",
-    "    head_gpus=0, # For GPU enabled workloads set the head_gpus and num_gpus\n",
-    "    num_gpus=0,\n",
+    "    head_extended_resource_requests={'nvidia.com/gpu':0}, # For GPU enabled workloads set the head_extended_resource_requests and worker_extended_resource_requests\n",
+    "    worker_extended_resource_requests={'nvidia.com/gpu':0},\n",
     "    num_workers=2,\n",
-    "    min_cpus=1,\n",
-    "    max_cpus=1,\n",
-    "    min_memory=4,\n",
-    "    max_memory=4,\n",
+    "    worker_cpu_requests=1,\n",
+    "    worker_cpu_limits=1,\n",
+    "    worker_memory_requests=4,\n",
+    "    worker_memory_limits=4,\n",
     "    # image=\"\", # Optional Field \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",

diff --git a/demo-notebooks/guided-demos/0_basic_ray.ipynb b/demo-notebooks/guided-demos/0_basic_ray.ipynb
@@ -64,13 +64,13 @@
     "    name='raytest', \n",
     "    head_cpus='500m',\n",
     "    head_memory=2,\n",
-    "    head_gpus=0, # For GPU enabled workloads set the head_gpus and num_gpus\n",
-    "    num_gpus=0,\n",
+    "    head_extended_resource_requests={'nvidia.com/gpu':0}, # For GPU enabled workloads set the head_extended_resource_requests and worker_extended_resource_requests\n",
+    "    worker_extended_resource_requests={'nvidia.com/gpu':0},\n",
     "    num_workers=2,\n",
-    "    min_cpus='250m',\n",
-    "    max_cpus=1,\n",
-    "    min_memory=4,\n",
-    "    max_memory=4,\n",
+    "    worker_cpu_requests='250m',\n",
+    "    worker_cpu_limits=1,\n",
+    "    worker_memory_requests=4,\n",
+    "    worker_memory_limits=4,\n",
     "    # image=\"\", # Optional Field \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",

diff --git a/demo-notebooks/guided-demos/1_cluster_job_client.ipynb b/demo-notebooks/guided-demos/1_cluster_job_client.ipynb
@@ -57,13 +57,13 @@
     "    name='jobtest',\n",
     "    head_cpus=1,\n",
     "    head_memory=4,\n",
-    "    head_gpus=1, # For GPU enabled workloads set the head_gpus and num_gpus\n",
-    "    num_gpus=1,\n",
+    "    head_extended_resource_requests={'nvidia.com/gpu':1}, # For GPU enabled workloads set the head_extended_resource_requests and worker_extended_resource_requests\n",
+    "    worker_extended_resource_requests={'nvidia.com/gpu':1},\n",
     "    num_workers=2,\n",
-    "    min_cpus='250m',\n",
-    "    max_cpus=1,\n",
-    "    min_memory=4,\n",
-    "    max_memory=4,\n",
+    "    worker_cpu_requests='250m',\n",
+    "    worker_cpu_limits=1,\n",
+    "    worker_memory_requests=4,\n",
+    "    worker_memory_limits=4,\n",
     "    # image=\"\", # Optional Field \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",

diff --git a/demo-notebooks/guided-demos/2_basic_interactive.ipynb b/demo-notebooks/guided-demos/2_basic_interactive.ipynb
@@ -62,13 +62,13 @@
     "    name=cluster_name,\n",
     "    head_cpus=1,\n",
     "    head_memory=6,\n",
-    "    head_gpus=1, # For GPU enabled workloads set the head_gpus and num_gpus\n",
-    "    num_gpus=1,\n",
+    "    head_extended_resource_requests={'nvidia.com/gpu':1}, # For GPU enabled workloads set the head_extended_resource_requests and worker_extended_resource_requests\n",
+    "    worker_extended_resource_requests={'nvidia.com/gpu':1},\n",
     "    num_workers=2,\n",
-    "    min_cpus='250m',\n",
-    "    max_cpus=1,\n",
-    "    min_memory=4,\n",
-    "    max_memory=6,\n",
+    "    worker_cpu_requests='250m',\n",
+    "    worker_cpu_limits=1,\n",
+    "    worker_memory_requests=4,\n",
+    "    worker_memory_limits=6,\n",
     "    # image=\"\", # Optional Field \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",

diff --git a/demo-notebooks/guided-demos/notebook-ex-outputs/0_basic_ray.ipynb b/demo-notebooks/guided-demos/notebook-ex-outputs/0_basic_ray.ipynb
@@ -70,13 +70,13 @@
     "# 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(\n",
     "    name='raytest',\n",
-    "    head_gpus=0, # For GPU enabled workloads set the head_gpus and num_gpus\n",
-    "    num_gpus=0,\n",
+    "    head_extended_resource_requests={'nvidia.com/gpu':0}, # For GPU enabled workloads set the head_extended_resource_requests and worker_extended_resource_requests\n",
+    "    worker_extended_resource_requests={'nvidia.com/gpu':0},\n",
     "    num_workers=2,\n",
-    "    min_cpus=1,\n",
-    "    max_cpus=1,\n",
-    "    min_memory=4,\n",
-    "    max_memory=4,\n",
+    "    worker_cpu_requests=1,\n",
+    "    worker_cpu_limits=1,\n",
+    "    worker_memory_requests=4,\n",
+    "    worker_memory_limits=4,\n",
     "    # image=\"\", # Optional Field \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",

diff --git a/demo-notebooks/guided-demos/notebook-ex-outputs/1_cluster_job_client.ipynb b/demo-notebooks/guided-demos/notebook-ex-outputs/1_cluster_job_client.ipynb
@@ -55,13 +55,13 @@
     "# 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(\n",
     "    name='jobtest',\n",
-    "    head_gpus=1, # For GPU enabled workloads set the head_gpus and num_gpus\n",
-    "    num_gpus=1,\n",
+    "    head_extended_resource_requests={'nvidia.com/gpu':1}, # For GPU enabled workloads set the head_extended_resource_requests and worker_extended_resource_requests\n",
+    "    worker_extended_resource_requests={'nvidia.com/gpu':1},\n",
     "    num_workers=2,\n",
-    "    min_cpus=1,\n",
-    "    max_cpus=1,\n",
-    "    min_memory=4,\n",
-    "    max_memory=4,\n",
+    "    worker_cpu_requests=1,\n",
+    "    worker_cpu_limits=1,\n",
+    "    worker_memory_requests=4,\n",
+    "    worker_memory_limits=4,\n",
     "    # image=\"\", # Optional Field \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",

diff --git a/demo-notebooks/guided-demos/notebook-ex-outputs/2_basic_interactive.ipynb b/demo-notebooks/guided-demos/notebook-ex-outputs/2_basic_interactive.ipynb
@@ -68,13 +68,13 @@
     "cluster_name = \"interactivetest\"\n",
     "cluster = Cluster(ClusterConfiguration(\n",
     "    name=cluster_name,\n",
-    "    head_gpus=1, # For GPU enabled workloads set the head_gpus and num_gpus\n",
-    "    num_gpus=1,\n",
+    "    head_extended_resource_requests={'nvidia.com/gpu':1}, # For GPU enabled workloads set the head_extended_resource_requests and worker_extended_resource_requests\n",
+    "    worker_extended_resource_requests={'nvidia.com/gpu':1},\n",
     "    num_workers=2,\n",
-    "    min_cpus=2,\n",
-    "    max_cpus=2,\n",
-    "    min_memory=8,\n",
-    "    max_memory=8,\n",
+    "    worker_cpu_requests=2,\n",
+    "    worker_cpu_limits=2,\n",
+    "    worker_memory_requests=8,\n",
+    "    worker_memory_limits=8,\n",
     "    # image=\"\", # Optional Field \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",

diff --git a/demo-notebooks/guided-demos/preview_nbs/0_basic_ray.ipynb b/demo-notebooks/guided-demos/preview_nbs/0_basic_ray.ipynb
@@ -62,13 +62,13 @@
     "# 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(\n",
     "    name='raytest',\n",
-    "    head_gpus=0, # For GPU enabled workloads set the head_gpus and num_gpus\n",
-    "    num_gpus=0,\n",
+    "    head_extended_resource_requests={'nvidia.com/gpu':0}, # For GPU enabled workloads set the head_extended_resource_requests and worker_extended_resource_requests\n",
+    "    worker_extended_resource_requests={'nvidia.com/gpu':0},\n",
     "    num_workers=2,\n",
-    "    min_cpus=1,\n",
-    "    max_cpus=1,\n",
-    "    min_memory=4,\n",
-    "    max_memory=4,\n",
+    "    worker_cpu_requests=1,\n",
+    "    worker_cpu_limits=1,\n",
+    "    worker_memory_requests=4,\n",
+    "    worker_memory_limits=4,\n",
     "    # image=\"\", # Optional Field \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",

diff --git a/demo-notebooks/guided-demos/preview_nbs/1_cluster_job_client.ipynb b/demo-notebooks/guided-demos/preview_nbs/1_cluster_job_client.ipynb
@@ -55,13 +55,13 @@
     "# 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(\n",
     "    name='jobtest',\n",
-    "    head_gpus=1, # For GPU enabled workloads set the head_gpus and num_gpus\n",
-    "    num_gpus=1,\n",
+    "    head_extended_resource_requests={'nvidia.com/gpu':1}, # For GPU enabled workloads set the head_extended_resource_requests and worker_extended_resource_requests\n",
+    "    worker_extended_resource_requests={'nvidia.com/gpu':1},\n",
     "    num_workers=2,\n",
-    "    min_cpus=1,\n",
-    "    max_cpus=1,\n",
-    "    min_memory=4,\n",
-    "    max_memory=4,\n",
+    "    worker_cpu_requests=1,\n",
+    "    worker_cpu_limits=1,\n",
+    "    worker_memory_requests=4,\n",
+    "    worker_memory_limits=4,\n",
     "    # image=\"\", # Optional Field \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",

diff --git a/demo-notebooks/guided-demos/preview_nbs/2_basic_interactive.ipynb b/demo-notebooks/guided-demos/preview_nbs/2_basic_interactive.ipynb
@@ -60,13 +60,13 @@
     "cluster_name = \"interactivetest\"\n",
     "cluster = Cluster(ClusterConfiguration(\n",
     "    name=cluster_name,\n",
-    "    head_gpus=1, # For GPU enabled workloads set the head_gpus and num_gpus\n",
-    "    num_gpus=1,\n",
+    "    head_extended_resource_requests={'nvidia.com/gpu':1}, # For GPU enabled workloads set the head_extended_resource_requests and worker_extended_resource_requests\n",
+    "    worker_extended_resource_requests={'nvidia.com/gpu':1},\n",
     "    num_workers=2,\n",
-    "    min_cpus=2,\n",
-    "    max_cpus=2,\n",
-    "    min_memory=8,\n",
-    "    max_memory=8,\n",
+    "    worker_cpu_requests=2,\n",
+    "    worker_cpu_limits=2,\n",
+    "    worker_memory_requests=8,\n",
+    "    worker_memory_limits=8,\n",
     "    # image=\"\", # Optional Field \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",

diff --git a/docs/cluster-configuration.md b/docs/cluster-configuration.md
@@ -11,14 +11,13 @@ cluster = Cluster(ClusterConfiguration(
     namespace='default', # Default None
     head_cpus=1, # Default 2
     head_memory=1, # Default 8
-    head_gpus=0, # Default 0
-    num_gpus=0, # Default 0
+    head_extended_resource_requests={'nvidia.com/gpu':0}, # Default 0
+    worker_extended_resource_requests={'nvidia.com/gpu':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
+    worker_cpu_requests=1, # Default 1
+    worker_cpu_limits=1, # Default 1
+    worker_memory_requests=2, # Default 2
+    worker_memory_limits=2, # Default 2
     # image="", # Optional Field
     machine_types=["m5.xlarge", "g4dn.xlarge"],
     labels={"exampleLabel": "example", "secondLabel": "example"},
@@ -28,4 +27,4 @@ Note: 'quay.io/rhoai/ray:2.23.0-py39-cu121' is the default community image used
 
 The `labels={"exampleLabel": "example"}` parameter can be used to apply additional labels to the RayCluster resource.
 
-After creating their`cluster`, a user can call `cluster.up()` and `cluster.down()` to respectively create or remove the Ray Cluster.
+After creating their `cluster`, a user can call `cluster.up()` and `cluster.down()` to respectively create or remove the Ray Cluster.