[auto-merge] branch-24.10 to branch-24.12 [skip ci] [bot]

README.md

@@ -5,10 +5,10 @@ RAPIDS Accelerator for Apache Spark accelerates Spark applications with no code
 You can download the latest version of RAPIDS Accelerator [here](https://nvidia.github.io/spark-rapids/docs/download.html).
 This repo contains examples and applications that showcases the performance and benefits of using 
 RAPIDS Accelerator in data processing and machine learning pipelines. 
-There are broadly four categories of examples in this repo: 
+There are broadly five categories of examples in this repo: 
 1. [SQL/Dataframe](./examples/SQL+DF-Examples) 
 2. [Spark XGBoost](./examples/XGBoost-Examples) 
-3. [Deep Learning/Machine Learning](./examples/ML+DL-Examples) 
+3. [Machine Learning/Deep Learning](./examples/ML+DL-Examples) 
 4. [RAPIDS UDF](./examples/UDF-Examples)
 5. [Databricks Tools demo notebooks](./tools/databricks)
 
@@ -23,7 +23,8 @@ Here is the list of notebooks in this repo:
 | 3 | XGBoost | Agaricus (Scala) | Uses XGBoost classifier function to create model that can accurately differentiate between edible and poisonous mushrooms with the [agaricus dataset](https://archive.ics.uci.edu/ml/datasets/mushroom)
 | 4 | XGBoost | Mortgage (Scala) | End-to-end ETL + XGBoost example to predict mortgage default with [Fannie Mae Single-Family Loan Performance Data](https://capitalmarkets.fanniemae.com/credit-risk-transfer/single-family-credit-risk-transfer/fannie-mae-single-family-loan-performance-data)
 | 5 | XGBoost | Taxi (Scala) | End-to-end ETL + XGBoost example to predict taxi trip fare amount with [NYC taxi trips data set](https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page)
-| 6 | ML/DL | PCA End-to-End | Spark MLlib based PCA example to train and transform with a synthetic dataset
+| 6 | ML/DL | PCA | [Spark-Rapids-ML](https://github.com/NVIDIA/spark-rapids-ml) based PCA example to train and transform with a synthetic dataset
+| 7 | ML/DL | DL Inference | 11 notebooks demonstrating distributed model inference on Spark using the `predict_batch_udf` across various frameworks: PyTorch, HuggingFace, and TensorFlow
 
 Here is the list of Apache Spark applications (Scala and PySpark) that 
 can be built for running on GPU with RAPIDS Accelerator in this repo:
@@ -33,7 +34,7 @@ can be built for running on GPU with RAPIDS Accelerator in this repo:
 | 1 | XGBoost | Agaricus (Scala) | Uses XGBoost classifier function to create model that can accurately differentiate between edible and poisonous mushrooms with the [agaricus dataset](https://archive.ics.uci.edu/ml/datasets/mushroom)
 | 2 | XGBoost | Mortgage (Scala) | End-to-end ETL + XGBoost example to predict mortgage default with [Fannie Mae Single-Family Loan Performance Data](https://capitalmarkets.fanniemae.com/credit-risk-transfer/single-family-credit-risk-transfer/fannie-mae-single-family-loan-performance-data)
 | 3 | XGBoost | Taxi (Scala) | End-to-end ETL + XGBoost example to predict taxi trip fare amount with [NYC taxi trips data set](https://www1.nyc.gov/site/tlc/about/tlc-trip-record-data.page)
-| 4 | ML/DL | PCA End-to-End | Spark MLlib based PCA example to train and transform with a synthetic dataset
+| 4 | ML/DL | PCA | [Spark-Rapids-ML](https://github.com/NVIDIA/spark-rapids-ml) based PCA example to train and transform with a synthetic dataset
 | 5 | UDF | URL Decode | Decodes URL-encoded strings using the [Java APIs of RAPIDS cudf](https://docs.rapids.ai/api/cudf-java/legacy/)
 | 6 | UDF | URL Encode | URL-encodes strings using the [Java APIs of RAPIDS cudf](https://docs.rapids.ai/api/cudf-java/legacy/)
 | 7 | UDF | [CosineSimilarity](./examples/UDF-Examples/RAPIDS-accelerated-UDFs/src/main/java/com/nvidia/spark/rapids/udf/java/CosineSimilarity.java) | Computes the cosine similarity between two float vectors using [native code](./examples/UDF-Examples/RAPIDS-accelerated-UDFs/src/main/cpp/src)

examples/ML+DL-Examples/Spark-DL/dl_inference/README.md

@@ -30,17 +30,49 @@ predictions = df.withColumn("preds", mnist("data")).collect()
 
 In this simple case, the `predict_batch_fn` will use TensorFlow APIs to load the model and return a simple `predict` function which operates on numpy arrays.  The `predict_batch_udf` will automatically convert the Spark DataFrame columns to the expected numpy inputs.
 
-All notebooks have been saved with sample outputs for quick browsing.
+All notebooks have been saved with sample outputs for quick browsing.  
+Here is a full list of the notebooks with their published example links:
+
+|   | Category  | Notebook Name | Description | Link
+| ------------- | ------------- | ------------- | ------------- | ------------- 
+| 1 | PyTorch | Image Classification | Training a model to predict clothing categories in FashionMNIST, including accelerated inference with Torch-TensorRT. | [Link](https://pytorch.org/tutorials/beginner/basics/quickstart_tutorial.html)
+| 2 | PyTorch | Regression | Training a model to predict housing prices in the California Housing Dataset, including accelerated inference with Torch-TensorRT. | [Link](https://github.com/christianversloot/machine-learning-articles/blob/main/how-to-create-a-neural-network-for-regression-with-pytorch.md)
+| 3 | Tensorflow | Image Classification | Training a model to predict hand-written digits in MNIST. | [Link](https://www.tensorflow.org/tutorials/keras/save_and_load)
+| 4 | Tensorflow | Feature Columns | Training a model with preprocessing layers to predict likelihood of pet adoption in the PetFinder mini dataset. | [Link](https://www.tensorflow.org/tutorials/structured_data/preprocessing_layers)
+| 5 | Tensorflow | Keras Metadata | Training ResNet-50 to perform flower recognition on Databricks. | [Link](https://docs.databricks.com/en/_extras/notebooks/source/deep-learning/keras-metadata.html)
+| 6 | Tensorflow | Text Classification | Training a model to perform sentiment analysis on the IMDB dataset. | [Link](https://www.tensorflow.org/tutorials/keras/text_classification)
+| 7+8 | HuggingFace | Conditional Generation | Sentence translation using the T5 text-to-text transformer, with notebooks demoing both Torch and Tensorflow. | [Link](https://huggingface.co/docs/transformers/model_doc/t5#t5) 
+| 9+10 | HuggingFace | Pipelines | Sentiment analysis using Huggingface pipelines, with notebooks demoing both Torch and Tensorflow. | [Link](https://huggingface.co/docs/transformers/quicktour#pipeline-usage)
+| 11 | HuggingFace | Sentence Transformers | Sentence embeddings using the SentenceTransformers framework in Torch. | [Link](https://huggingface.co/sentence-transformers)
 
 ## Running the Notebooks
 
 If you want to run the notebooks yourself, please follow these instructions.
 
-**Note**: for demonstration purposes, these examples just use a local Spark Standalone cluster with a single executor, but you should be able to run them on any distributed Spark cluster.
+**Notes**: 
+- The notebooks require a GPU environment for the executors.  
+- Please create separate environments for PyTorch and Tensorflow examples as specified below. This will avoid conflicts between the CUDA libraries bundled with their respective versions. The Huggingface examples will have a `_torch` or `_tf` suffix to specify the environment used.
+- The PyTorch notebooks include model compilation and accelerated inference with TensorRT. While not included in the notebooks, Tensorflow also supports [integration with TensorRT](https://docs.nvidia.com/deeplearning/frameworks/tf-trt-user-guide/index.html), but may require downgrading the TF version. 
+- For demonstration purposes, these examples just use a local Spark Standalone cluster with a single executor, but you should be able to run them on any distributed Spark cluster.
+
+#### Create environment
+
+**For PyTorch:**
+```
+conda create -n spark-dl-torch python=3.11
+conda activate spark-dl-torch
+pip install -r torch_requirements.txt
+```
+**For TensorFlow:**
 ```
-# install dependencies for example notebooks
-pip install -r requirements.txt
+conda create -n spark-dl-tf python=3.11
+conda activate spark-dl-tf
+pip install -r tf_requirements.txt
+```
+
+#### Launch Jupyter + Spark
 
+```
 # setup environment variables
 export SPARK_HOME=/path/to/spark
 export MASTER=spark://$(hostname):7077
@@ -70,4 +102,4 @@ The example notebooks also demonstrate integration with [Triton Inference Server
 
 **Note**: Some examples may require special configuration of server as highlighted in the notebooks.
 
-**Note**: for demonstration purposes, the Triton Inference Server integrations just launch the server in a docker container on the local host, so you will need to [install docker](https://docs.docker.com/engine/install/) on your local host.  Most real-world deployments will likely be hosted on remote machines.
+**Note**: for demonstration purposes, the Triton Inference Server integrations just launch the server in a docker container on the local host, so you will need to [install docker](https://docs.docker.com/engine/install/) on your local host.  Most real-world deployments will likely be hosted on remote machines.