Merge branch 'main' into sramakr1/refactor_xpu_layers

Author: sramakintel

.github/workflows/container-ci.yaml

@@ -158,6 +158,10 @@ jobs:
     #     password: ${{ secrets.REGISTRY_TOKEN }}
     - name: Pull Image
       run: docker pull ${{ secrets.REGISTRY }}/${{ secrets.REPO }}:${{ matrix.container }}
+    - uses: actions/cache@3624ceb22c1c5a301c8db4169662070a689d9ea8 # v4.1.1
+      with:
+        path: ${{ github.workspace }}/.cache/trivy
+        key: ${{ github.head_ref || github.ref_name }}-trivy
     - name: Scan Container
       uses: aquasecurity/trivy-action@915b19bbe73b92a6cf82a1bc12b087c9a19a5fe2 # v0.28.0
       with:

jax/README.md

@@ -8,13 +8,13 @@ The images below include [JAX\*] and [Intel® Extension for OpenXLA\*].
 
 | Tag(s)                     | [JAX\*]   | [Intel® Extension for OpenXLA\*] | [Flax]   | Dockerfile      |
 | -------------------------- | --------- | -------------------------------- | -------- | --------------- |
-| `0.4.0-pip-base`, `latest` | [v0.4.32] | [v0.4.0-jax]                     | [v0.9.0] | [v0.4.0]        |
+| `0.4.0-pip-base`, `latest` | [v0.4.26] | [v0.4.0-jax]                     | [v0.8.2] | [v0.4.1]        |
 
 The images below additionally include [Jupyter Notebook](https://jupyter.org/) server:
 
 | Tag(s)              | [JAX\*]   | [Intel® Extension for OpenXLA\*] | [Flax]   | Dockerfile      |
 | ------------------- | --------- | ----------------- | -------- | --------------- |
-| `0.4.0-pip-jupyter` | [v0.4.32] | [v0.4.0-jax]      | [v0.9.0] | [v0.4.0]        |
+| `0.4.0-pip-jupyter` | [v0.4.26] | [v0.4.0-jax]      | [v0.8.2] | [v0.4.1]        |
 
 ### Run the Jupyter Container
 
@@ -35,13 +35,13 @@ The images below include [Intel® Distribution for Python*]:
 
 | Tag(s)           | [JAX\*]   | [Intel® Extension for OpenXLA\*] | [Flax]   | Dockerfile      |
 | ---------------- | --------- | ----------------- | -------- | --------------- |
-| `0.4.0-idp-base` | [v0.4.32] | [v0.4.0-jax]      | [v0.9.0] | [v0.4.0]        |
+| `0.4.0-idp-base` | [v0.4.26] | [v0.4.0-jax]      | [v0.8.2] | [v0.4.1]        |
 
 The images below additionally include [Jupyter Notebook](https://jupyter.org/) server:
 
 | Tag(s)              | [JAX\*]   | [Intel® Extension for OpenXLA\*] | [Flax]   | Dockerfile      |
 | ------------------- | --------- | ----------------- | -------- | --------------- |
-| `0.4.0-idp-jupyter` | [v0.4.32] | [v0.4.0-jax]      | [v0.9.0] | [v0.4.0]        |
+| `0.4.0-idp-jupyter` | [v0.4.26] | [v0.4.0-jax]      | [v0.8.2] | [v0.4.1]        |
 
 ## Build from Source
 
@@ -77,10 +77,10 @@ It is the image user's responsibility to ensure that any use of The images below
 [JAX\*]: https://github.com/google/jax
 [Flax]: https://github.com/google/flax
 
-[v0.4.32]: https://github.com/google/jax/releases/tag/jax-v0.4.32
+[v0.4.26]: https://github.com/google/jax/releases/tag/jax-v0.4.26
 
 [v0.4.0-jax]: https://github.com/intel/intel-extension-for-openxla/releases/tag/0.4.0
 
-[v0.9.0]: https://github.com/google/Flax/releases/tag/v0.9.0
+[v0.8.2]: https://github.com/google/Flax/releases/tag/v0.8.2
 
-[v0.4.0]: https://github.com/intel/ai-containers/blob/v0.4.0/jax/Dockerfile
+[v0.4.1]: https://github.com/intel/ai-containers/blob/main/jax/Dockerfile

workflows/charts/tensorflow-serving/Chart.yaml

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 apiVersion: v2
-name: tensorflow-serving-on-intel
+name: tensorflow-serving
 description: TensorFlow Serving is a flexible, high-performance serving system for machine learning models, designed for production environments. TensorFlow Serving makes it easy to deploy new algorithms and experiments, while keeping the same server architecture and APIs. TensorFlow Serving provides out-of-the-box integration with TensorFlow models, but can be easily extended to serve other types of models and data.
 
 # A chart can be either an 'application' or a 'library' chart.

workflows/charts/tensorflow-serving/README.md

@@ -1,14 +1,17 @@
-# tensorflow-serving-on-intel
+# TensorFlow Serving on Intel GPU
+
+TensorFlow Serving is a flexible, high-performance serving system for machine learning models, designed for production environments. TensorFlow Serving makes it easy to deploy new algorithms and experiments, while keeping the same server architecture and APIs. TensorFlow Serving provides out-of-the-box integration with TensorFlow models, but can be easily extended to serve other types of models and data.
 
 ![Version: 0.1.0](https://img.shields.io/badge/Version-0.1.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 1.16.0](https://img.shields.io/badge/AppVersion-1.16.0-informational?style=flat-square)
 
-TensorFlow Serving is a flexible, high-performance serving system for machine learning models, designed for production environments. TensorFlow Serving makes it easy to deploy new algorithms and experiments, while keeping the same server architecture and APIs. TensorFlow Serving provides out-of-the-box integration with TensorFlow models, but can be easily extended to serve other types of models and data.
+## Installation
 
-## Maintainers
+```bash
+helm repo add intel https://intel.github.io/helm-charts
+helm install my-tgi intel/text-generation-inference
+```
 
-| Name | Email | Url |
-| ---- | ------ | --- |
-| tylertitsworth | <tyler.titsworth@intel.com> | <https://github.com/tylertitsworth> |
+Then, follow the installation notes to test the deployment
 
 ## Values
 

workflows/charts/tensorflow-serving/README.md.gotmpl

@@ -0,0 +1,18 @@
+# TensorFlow Serving on Intel GPU
+
+{{ template "chart.description" . }}
+
+{{ template "chart.versionBadge" . }}{{ template "chart.typeBadge" . }}{{ template "chart.appVersionBadge" . }}
+
+## Installation
+
+```bash
+helm repo add intel https://intel.github.io/helm-charts
+helm install my-tgi intel/text-generation-inference
+```
+
+Then, follow the installation notes to test the deployment
+
+{{ template "chart.valuesSection" . }}
+
+{{ template "helm-docs.versionFooter" . }}

workflows/charts/tgi/.helmignore workflows/charts/text-generation-inference/.helmignore

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 apiVersion: v2
-name: tgi-on-intel
+name: text-generation-inference
 description: A Rust, Python and gRPC server for text generation inference by huggingface on Intel GPUs.
 
 # A chart can be either an 'application' or a 'library' chart.

workflows/charts/tgi/Chart.yaml workflows/charts/text-generation-inference/Chart.yaml

@@ -9,6 +9,15 @@ For more information about how to use Huggingface text-generation-inference with
 
 ![Version: 0.2.1](https://img.shields.io/badge/Version-0.2.1-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 1.16.0](https://img.shields.io/badge/AppVersion-1.16.0-informational?style=flat-square)
 
+## Installation
+
+```bash
+helm repo add intel https://intel.github.io/helm-charts
+helm install my-tgi intel/text-generation-inference
+```
+
+Then, follow the installation notes to test the deployment
+
 ## Values
 
 | Key | Type | Default | Description |

workflows/charts/tgi/README.md workflows/charts/text-generation-inference/README.md

@@ -9,7 +9,14 @@ For more information about how to use Huggingface text-generation-inference with
 
 {{ template "chart.versionBadge" . }}{{ template "chart.typeBadge" . }}{{ template "chart.appVersionBadge" . }}
 
-{{ template "chart.requirementsSection" . }}
+## Installation
+
+```bash
+helm repo add intel https://intel.github.io/helm-charts
+helm install my-tgi intel/text-generation-inference
+```
+
+Then, follow the installation notes to test the deployment
 
 {{ template "chart.valuesSection" . }}
 

workflows/charts/tgi/README.md.gotmpl workflows/charts/text-generation-inference/README.md.gotmpl

@@ -13,8 +13,8 @@
 # limitations under the License.
 
 apiVersion: v2
-name: torchserve-on-intel
-description: TorchServe on Intel is a performant, flexible and easy to use tool for serving PyTorch models in production.
+name: torchserve
+description: TorchServe is a performant, flexible and easy to use tool for serving PyTorch models in production on Intel GPUs.
 
 # A chart can be either an 'application' or a 'library' chart.
 #

workflows/charts/tgi/templates/NOTES.txt workflows/charts/text-generation-inference/templates/NOTES.txt

@@ -1,11 +1,20 @@
 # TorchServe with Intel Optimizations
 
-TorchServe on Intel is a performant, flexible and easy to use tool for serving PyTorch models in production.
+TorchServe is a performant, flexible and easy to use tool for serving PyTorch models in production on Intel GPUs.
 
-For more information about how to use TorchServe with Intel Optimizations, check out the [container documentation](../../../pytorch/serving/README.md).
+For more information about how to use TorchServe with Intel Optimizations, check out the [container documentation](https://github.com/intel/ai-containers/blob/main/pytorch/serving/README.md).
 
 ![Version: 0.1.0](https://img.shields.io/badge/Version-0.1.0-informational?style=flat-square) ![Type: application](https://img.shields.io/badge/Type-application-informational?style=flat-square) ![AppVersion: 1.16.0](https://img.shields.io/badge/AppVersion-1.16.0-informational?style=flat-square)
 
+## Installation
+
+```bash
+helm repo add intel https://intel.github.io/helm-charts
+helm install my-tgi intel/text-generation-inference
+```
+
+Then, follow the installation notes to test the deployment
+
 ## Values
 
 | Key | Type | Default | Description |

workflows/charts/tgi/templates/_helpers.tpl workflows/charts/text-generation-inference/templates/_helpers.tpl

@@ -2,11 +2,18 @@
 
 {{ template "chart.description" . }}
 
-For more information about how to use TorchServe with Intel Optimizations, check out the [container documentation](../../../pytorch/serving/README.md).
+For more information about how to use TorchServe with Intel Optimizations, check out the [container documentation](https://github.com/intel/ai-containers/blob/main/pytorch/serving/README.md).
 
 {{ template "chart.versionBadge" . }}{{ template "chart.typeBadge" . }}{{ template "chart.appVersionBadge" . }}
 
-{{ template "chart.requirementsSection" . }}
+## Installation
+
+```bash
+helm repo add intel https://intel.github.io/helm-charts
+helm install my-tgi intel/text-generation-inference
+```
+
+Then, follow the installation notes to test the deployment
 
 {{ template "chart.valuesSection" . }}