[serve] remove GPT-J example

ci/ray_ci/ml.tests.yml

@@ -3,4 +3,3 @@ flaky_tests:
   - //python/ray/train:horovod_cifar_pbt_example
   # doc tests
   # gpu tests
-  - //doc/source/ray-air/examples:gptj_serving

doc/source/data/examples/gptj_batch_prediction.ipynb

@@ -13,8 +13,6 @@
     "\n",
     "It is highly recommended to read [Ray Train Key Concepts](train-key-concepts) and [Ray Data Key Concepts](data_key_concepts) before starting this example.\n",
     "\n",
-    "If you are interested in serving (online inference), see {doc}`/ray-air/examples/gptj_serving`.\n",
-    "\n",
     "```{note}\n",
     "In order to run this example, make sure your Ray cluster has access to at least one GPU with 16 or more GBs of memory. The amount of memory needed will depend on the model.\n",
     "```"

doc/source/ray-overview/examples.rst

@@ -131,13 +131,6 @@ Ray Examples
 
         How to use Ray Data to do batch prediction with the Hugging Face Transformers GPT-J model
 
-    .. grid-item-card:: :bdg-secondary:`Code example`
-        :class-item: gallery-item serving large-language-models generative-ai
-        :link: /ray-air/examples/gptj_serving
-        :link-type: doc
-
-        How to use Ray Serve to do online serving with the Hugging Face Transformers GPT-J model
-
     .. grid-item-card:: :bdg-secondary:`Code example`
         :class-item: gallery-item computer-vision training generative-ai
         :link: /train/examples/pytorch/dreambooth_finetuning

doc/source/splash.html

@@ -328,6 +328,7 @@ <h2 style="font-weight: 600">Scaling with Ray</h2>
             <a href="./serve/api/index.html" target="_blank">API references</a>
           </div>
           <div class="col-6" style="display: flex; justify-content: flex-end">
+            <!-- TODO: Update this to diffrent example. -->
             <a
               href="https://github.com/ray-project/ray/blob/master/doc/source/ray-air/examples/gptj_serving.ipynb"
               target="_blank"