update sdk and demos to ray 2.5

custom-nb-image/imagestream.yaml

@@ -21,7 +21,7 @@ metadata:
   annotations:
     opendatahub.io/notebook-image-name:
       "CodeFlare Notebook"
-    opendatahub.io/notebook-image-desc: "Custom Jupyter notebook image with CodeFlare SDK, Python 3.8, Ray 2.1.0 and PyTorch 1.12.1"
+    opendatahub.io/notebook-image-desc: "Custom Jupyter notebook image with CodeFlare SDK, Python 3.8, Ray 2.5.0 and PyTorch 1.12.1"
 spec:
   lookupPolicy:
     local: true

custom-nb-image/requirements.txt

@@ -157,7 +157,7 @@ python-json-logger==2.0.4; python_version >= '3.5'
 pytz==2022.2.1
 pyyaml==6.0; python_version >= '3.6'
 pyzmq==24.0.1; python_version >= '3.6'
-ray[default]==2.1.0
+ray[default]==2.5.0
 requests-oauthlib==1.3.1; python_version >= '2.7' and python_version not in '3.0, 3.1, 3.2, 3.3'
 requests==2.28.1; python_version >= '3.7' and python_version < '4'
 rsa==4.9; python_version >= '3.6'

demo-notebooks/batch-job/batch_mnist_ray.ipynb

@@ -63,6 +63,7 @@
     "    min_memory=16,\n",
     "    max_memory=16,\n",
     "    gpu=4,\n",
+    "    image=\"quay.io/project-codeflare/ray:2.5.0-py38-cu116\",\n",
     "    instascale=True, # Can be set to false if scaling not needed\n",
     "    machine_types=[\"m5.xlarge\", \"g4dn.xlarge\"] # Can be removed if above is false\n",
     "))"
@@ -88,7 +89,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "657ebdfb",
    "metadata": {},
@@ -222,7 +222,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "b3a55fe4",
    "metadata": {},
@@ -5224,7 +5223,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "sdktest",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },

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

@@ -1,7 +1,6 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "8d4a42f6",
    "metadata": {},
@@ -65,6 +64,7 @@
     "    max_cpus=1,\n",
     "    min_memory=4,\n",
     "    max_memory=4,\n",
+    "    image=\"quay.io/project-codeflare/ray:2.5.0-py38-cu116\",\n",
     "    gpu=0,\n",
     "    instascale=False\n",
     "))"
@@ -90,7 +90,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "657ebdfb",
    "metadata": {},
@@ -129,7 +128,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "b3a55fe4",
    "metadata": {},
@@ -178,7 +176,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -192,7 +190,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.13"
+   "version": "3.8.13"
   },
   "vscode": {
    "interpreter": {

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

@@ -1,7 +1,6 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "9865ee8c",
    "metadata": {},
@@ -38,7 +37,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "bc27f84c",
    "metadata": {},
@@ -64,13 +62,13 @@
     "    min_memory=8,\n",
     "    max_memory=8,\n",
     "    gpu=1,\n",
+    "    image=\"quay.io/project-codeflare/ray:2.5.0-py38-cu116\",\n",
     "    instascale=True, # InstaScale now enabled, will scale OCP cluster to guarantee resource request\n",
     "    machine_types=[\"m5.xlarge\", \"g4dn.xlarge\"] # Head, worker AWS machine types desired\n",
     "))"
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "12eef53c",
    "metadata": {},
@@ -91,7 +89,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "6abfe904",
    "metadata": {},
@@ -130,7 +127,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "c883caea",
    "metadata": {},
@@ -151,7 +147,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -165,7 +161,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.13"
+   "version": "3.8.13"
   },
   "vscode": {
    "interpreter": {

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

@@ -1,7 +1,6 @@
 {
  "cells": [
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "464af595",
    "metadata": {},
@@ -38,7 +37,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "bc27f84c",
    "metadata": {},
@@ -64,6 +62,7 @@
     "    min_memory=4,\n",
     "    max_memory=4,\n",
     "    gpu=0,\n",
+    "    image=\"quay.io/project-codeflare/ray:2.5.0-py38-cu116\",\n",
     "    instascale=False\n",
     "))"
    ]
@@ -91,7 +90,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "33663f47",
    "metadata": {},
@@ -110,7 +108,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "83d77b74",
    "metadata": {},
@@ -134,7 +131,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "5b9ae53a",
    "metadata": {},
@@ -163,7 +159,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "5af8cd32",
    "metadata": {},
@@ -182,7 +177,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "31096641",
    "metadata": {},
@@ -211,7 +205,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "0837e43b",
    "metadata": {},
@@ -240,7 +233,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "aebf376a",
    "metadata": {},
@@ -271,7 +263,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -285,7 +277,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.13"
+   "version": "3.8.13"
   },
   "vscode": {
    "interpreter": {

demo-notebooks/guided-demos/3_basic_interactive.ipynb

@@ -62,6 +62,7 @@
     "    min_memory=8,\n",
     "    max_memory=8,\n",
     "    gpu=1,\n",
+    "    image=\"quay.io/project-codeflare/ray:2.5.0-py38-cu116\",\n",
     "    instascale=True,\n",
     "    machine_types=[\"m5.xlarge\", \"g4dn.xlarge\"]\n",
     "    \n",
@@ -275,7 +276,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -289,7 +290,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.13"
+   "version": "3.8.13"
   },
   "vscode": {
    "interpreter": {

demo-notebooks/guided-demos/4_gpt.ipynb

@@ -45,6 +45,7 @@
     "    min_memory=8,\n",
     "    max_memory=8,\n",
     "    gpu=1,\n",
+    "    image=\"quay.io/project-codeflare/ray:2.5.0-py38-cu116\",\n",
     "    instascale=True,\n",
     "    machine_types=[\"m5.xlarge\", \"g4dn.xlarge\"],\n",
     "))"

demo-notebooks/interactive/hf_interactive.ipynb

@@ -86,7 +86,17 @@
    ],
    "source": [
     "# Create our cluster and submit appwrapper\n",
-    "cluster = Cluster(ClusterConfiguration(name='hfgputest', min_worker=1, max_worker=1, min_cpus=8, max_cpus=8, min_memory=16, max_memory=16, gpu=4, instascale=True, machine_types=[\"m5.xlarge\", \"p3.8xlarge\"]))"
+    "cluster = Cluster(ClusterConfiguration(name='hfgputest', \n",
+    "                                       namespace=\"default\",\n",
+    "                                       min_worker=1, \n",
+    "                                       max_worker=1, \n",
+    "                                       min_cpus=8, \n",
+    "                                       max_cpus=8, \n",
+    "                                       min_memory=16, \n",
+    "                                       max_memory=16, \n",
+    "                                       gpu=4,\n",
+    "                                       image=\"quay.io/project-codeflare/ray:2.5.0-py38-cu116\",\n",
+    "                                       instascale=True, machine_types=[\"m5.xlarge\", \"p3.8xlarge\"]))"
    ]
   },
   {
@@ -108,7 +118,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "657ebdfb",
    "metadata": {},
@@ -189,7 +198,6 @@
    ]
   },
   {
-   "attachments": {},
    "cell_type": "markdown",
    "id": "477ac246",
    "metadata": {},
@@ -309,7 +317,7 @@
     "# establish connection to ray cluster\n",
     "\n",
     "#install additionall libraries that will be required for this training\n",
-    "runtime_env = {\"pip\": [\"transformers\", \"datasets\", \"evaluate\"]}\n",
+    "runtime_env = {\"pip\": [\"transformers\", \"datasets\", \"evaluate\", \"pyarrow<7.0.0\", \"accelerate\"]}\n",
     "\n",
     "ray.init(address=f'{ray_cluster_uri}', runtime_env=runtime_env)\n",
     "\n",
@@ -1443,7 +1451,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3.9.7 64-bit",
+   "display_name": "Python 3 (ipykernel)",
    "language": "python",
    "name": "python3"
   },
@@ -1457,7 +1465,7 @@
    "name": "python",
    "nbconvert_exporter": "python",
    "pygments_lexer": "ipython3",
-   "version": "3.9.13"
+   "version": "3.8.13"
   },
   "vscode": {
    "interpreter": {

pyproject.toml

@@ -23,8 +23,8 @@ keywords = ['codeflare', 'python', 'sdk', 'client', 'batch', 'scale']
 python = "^3.7"
 openshift-client = "1.0.18"
 rich = "^12.5"
-ray = {version = "2.1.0", extras = ["default"]}
-kubernetes = ">= 25.3.0, < 27"
+ray = {version = "2.5.0", extras = ["default"]}
+kubernetes = "25.3.0"
 codeflare-torchx = "0.6.0.dev0"
 cryptography = "40.0.2"
 

requirements.txt

@@ -1,5 +1,5 @@
 openshift-client==1.0.18
 rich==12.5.1
-ray[default]==2.1.0
+ray[default]==2.5.0
 kubernetes>=25.3.0,<27
 codeflare-torchx==0.6.0.dev0

src/codeflare_sdk/cluster/config.py

@@ -47,6 +47,6 @@ class ClusterConfiguration:
     template: str = f"{dir}/templates/base-template.yaml"
     instascale: bool = False
     envs: dict = field(default_factory=dict)
-    image: str = "ghcr.io/foundation-model-stack/base:ray2.1.0-py38-gpu-pytorch1.12.0cu116-20221213-193103"
+    image: str = "quay.io/project-codeflare/ray:2.5.0-py38-cu116"
     local_interactive: bool = False
     image_pull_secrets: list = field(default_factory=list)