Merge remote-tracking branch 'upstream/main'

Author: dchourasia

README.md

@@ -22,7 +22,7 @@
 * `CODEFLARE_TEST_TIMEOUT_LONG` - Timeout duration for long tasks
 * `CODEFLARE_TEST_RAY_IMAGE` (Optional) - Ray image used for raycluster configuration 
 
-    NOTE: `quay.io/rhoai/ray:2.23.0-py39-cu121` is the default community image used for creating a raycluster resource. If you have your own custom ray image which suits your purposes, specify it in `CODEFLARE_TEST_RAY_IMAGE` environment variable.
+    NOTE: `quay.io/modh/ray:2.35.0-py39-cu121` is the default image used for creating a RayCluster resource. If you have your own custom ray image which suits your purposes, specify it in `CODEFLARE_TEST_RAY_IMAGE` environment variable.
 
 ### Environment variables for Training operator test suite
 

examples/hpo-raytune/notebook/raytune-oai-MR-gRPC-demo.ipynb

@@ -43,8 +43,9 @@
    "outputs": [],
    "source": [
     "# Create and configure our cluster object (and appwrapper)\n",
+    "cluster_name='terrestrial-raytest'\n",
     "cluster = Cluster(ClusterConfiguration(\n",
-    "    name='terrestial-raytest',\n",
+    "    name=cluster_name,\n",
     "    head_cpus=1,\n",
     "    head_memory=4,\n",
     "    num_workers=2,\n",
@@ -53,7 +54,7 @@
     "    min_memory=4,\n",
     "    max_memory=4,\n",
     "    num_gpus=0,\n",
-    "    image=\"quay.io/rhoai/ray:2.23.0-py39-cu121\"\n",
+    "    image=\"quay.io/modh/ray:2.35.0-py39-cu121\"\n",
     "))"
    ]
   },
@@ -92,8 +93,8 @@
    "source": [
     "from codeflare_sdk import generate_cert\n",
     "# Create required TLS cert and export the environment variables to enable TLS\n",
-    "generate_cert.generate_tls_cert(cluster_name, namespace)\n",
-    "generate_cert.export_env(cluster_name, namespace)"
+    "generate_cert.generate_tls_cert(cluster_name, cluster.config.namespace)\n",
+    "generate_cert.export_env(cluster_name, cluster.config.namespace)"
    ]
   },
   {
@@ -104,7 +105,7 @@
    "outputs": [],
    "source": [
     "!pip install numpy\n",
-    "!pip install ray[default]==2.7.0\n",
+    "!pip install ray[default]==2.35.0\n",
     "!pip install onnxruntime\n",
     "!pip install ml_metadata"
    ]

examples/hpo-raytune/notebook/raytune-oai-demo-mlmd.ipynb

@@ -43,8 +43,9 @@
    "outputs": [],
    "source": [
     "# Create and configure our cluster object (and appwrapper)\n",
+    "cluster_name='terrestrial-raytest'\n",
     "cluster = Cluster(ClusterConfiguration(\n",
-    "    name='terrestial-raytest',\n",
+    "    name=cluster_name,\n",
     "    head_cpus=1,\n",
     "    head_memory=4,\n",
     "    num_workers=2,\n",
@@ -53,7 +54,7 @@
     "    min_memory=4,\n",
     "    max_memory=4,\n",
     "    num_gpus=0,\n",
-    "    image=\"quay.io/rhoai/ray:2.23.0-py39-cu121\",                                           \n",
+    "    image=\"quay.io/modh/ray:2.35.0-py39-cu121\",                                           \n",
     "))"
    ]
   },
@@ -92,8 +93,8 @@
    "source": [
     "from codeflare_sdk import generate_cert\n",
     "# Create required TLS cert and export the environment variables to enable TLS\n",
-    "generate_cert.generate_tls_cert(cluster_name, namespace)\n",
-    "generate_cert.export_env(cluster_name, namespace)"
+    "generate_cert.generate_tls_cert(cluster_name, cluster.config.namespace)\n",
+    "generate_cert.export_env(cluster_name, cluster.config.namespace)"
    ]
   },
   {
@@ -104,7 +105,7 @@
    "outputs": [],
    "source": [
     "!pip install numpy\n",
-    "!pip install ray[default]==2.7.0\n",
+    "!pip install ray[default]==2.35.0\n",
     "!pip install onnxruntime\n",
     "!pip install ml_metadata"
    ]

examples/hpo-raytune/notebook/raytune-oai-demo.ipynb

@@ -44,8 +44,9 @@
    "outputs": [],
    "source": [
     "# Create and configure our cluster object (and appwrapper)\n",
+    "cluster_name=\"terrestrial-raytest\"\n",
     "cluster = Cluster(ClusterConfiguration(\n",
-    "    name='terrestial-raytest',\n",
+    "    name=cluster_name,\n",
     "    head_cpus=1,\n",
     "    head_memory=4,\n",
     "    num_workers=2,\n",
@@ -54,7 +55,7 @@
     "    min_memory=4,\n",
     "    max_memory=4,\n",
     "    num_gpus=0,\n",
-    "    image=\"quay.io/rhoai/ray:2.23.0-py39-cu121\"\n",
+    "    image=\"quay.io/modh/ray:2.35.0-py39-cu121\"\n",
     "))"
    ]
   },
@@ -93,8 +94,8 @@
    "source": [
     "from codeflare_sdk import generate_cert\n",
     "# Create required TLS cert and export the environment variables to enable TLS\n",
-    "generate_cert.generate_tls_cert(cluster_name, namespace)\n",
-    "generate_cert.export_env(cluster_name, namespace)"
+    "generate_cert.generate_tls_cert(cluster_name, cluster.config.namespace)\n",
+    "generate_cert.export_env(cluster_name, cluster.config.namespace)"
    ]
   },
   {
@@ -105,8 +106,9 @@
    "outputs": [],
    "source": [
     "!pip install numpy\n",
-    "!pip install ray[default]==2.7.0\n",
-    "!pip install onnxruntime"
+    "!pip install ray[default]==2.35.0\n",
+    "!pip install onnxruntime\n",
+    "!pip install --upgrade pyarrow fsspec"
    ]
   },
   {

examples/stable-diffusion-dreambooth/notebook/raycluster.yaml

@@ -46,7 +46,7 @@ spec:
           - name: shared-storage
             persistentVolumeClaim:
               claimName: stable-diffusion-shared-storage
-  rayVersion: 2.7.0
+  rayVersion: 2.35.0
   suspend: false
   workerGroupSpecs:
     - groupName: small-group-stable-diffusion

images/runtime/examples/ray-torch-cuda/Dockerfile

@@ -1,4 +1,4 @@
-FROM quay.io/rhoai/ray:2.35.0-py39-cu121
+FROM quay.io/modh/ray:2.35.0-py39-cu121
 
 # Install PyTorch
 RUN python3 -m pip install torch==2.4.0

images/runtime/examples/ray-torch-rocm/Dockerfile

@@ -1,4 +1,4 @@
-FROM quay.io/rhoai/ray:2.35.0-py39-rocm61
+FROM quay.io/modh/ray:2.35.0-py39-rocm61
 
 ENV PYTORCH_ROCM_ARCH=gfx942