Updated the documentation with Intel AI Accelerator instead of Gaudi since stack supports all Intel accelerators (opea-project#79)

* Update prerequisites.md

* Update and rename gaudi-prerequisites.md to intel-ai-accelerator-prerequisites.md

* Rename Enterprise-Inference-Gaudi-Driver-version.png to Enterprise-Inference-Intel-AI-Accelerator-Driver-version.png

* Rename Enterprise-Inference-Gaudi-Firmware-version.png to Enterprise-Inference-Intel-AI-Accelerator-Firmware-version.png

* Update and rename einf-singlenode-gaudi.yml to einf-singlenode-intel-ai-accelerator.yml

* Update README.md

* Update single-node-deployment.md

* Update cpu-optimization-guide.md

* Update deploy-llm-model-from-hugging-face.md

* Update README.md

* Update inventory-design-guide.md

* Update inventory-design-guide.md

* Update inventory-design-guide.md

* Update inventory-design-guide.md

* Update inventory-design-guide.md

* Update configuring-inference-config-cfg-file.md

* Update multi-node-deployment.md

* Update einf-singlenode-xeon.yml

* Rename Enterprise-Inference-Gaudi-Utilization-Cluster-Observability.png to Enterprise-Inference-Intel-AI-Accelerator-Utilization-Cluster-Observability.png

* Rename Enterprise-Inference-Gaudi-Observability.png to Enterprise-Inference-Intel-AI-Accelerator-Observability.png

* Rename Enterprise-Inference-Gaudi-Habana-version.png to Enterprise-Inference-Intel-AI-Accelerator-Habana-version.png

* Update AI Accelerator documentation

Signed-off-by: psurabh <pradeep.surabhi@intel.com>
Signed-off-by: amberjain1 <amber.jain@intel.com>
Signed-off-by: mdfaheem-intel <mohammad.faheem@intel.com>
Signed-off-by: vivekrsintc <vivek.rs@intel.com>
Co-authored-by: pvishwan <pramodh.vishwanath@intel.com>
Co-authored-by: AhmedSeemalK <ahmed.seemal@intel.com>
Co-authored-by: vhpintel <vijay.kumar.h.p@intel.com>
Co-authored-by: sgurunat <gurunath.s@intel.com>
Co-authored-by: jaswanth8888 <jaswanth.karani@intel.com>
Co-authored-by: sandeshk-intel <sandesh.kumar.s@intel.com>
Co-authored-by: vinayK34 <vinay3.kumar@intel.com>
Signed-off-by: Github Actions <actions@github.com>

---------

Signed-off-by: psurabh <pradeep.surabhi@intel.com>
Signed-off-by: amberjain1 <amber.jain@intel.com>
Signed-off-by: mdfaheem-intel <mohammad.faheem@intel.com>
Signed-off-by: vivekrsintc <vivek.rs@intel.com>
Signed-off-by: Github Actions <actions@github.com>
Co-authored-by: pvishwan <pramodh.vishwanath@intel.com>
Co-authored-by: AhmedSeemalK <ahmed.seemal@intel.com>
Co-authored-by: vhpintel <vijay.kumar.h.p@intel.com>
Co-authored-by: sgurunat <gurunath.s@intel.com>
Co-authored-by: jaswanth8888 <jaswanth.karani@intel.com>
Co-authored-by: sandeshk-intel <sandesh.kumar.s@intel.com>
Co-authored-by: vinayK34 <vinay3.kumar@intel.com>

Author: 8 people

docs/README.md

@@ -1,7 +1,7 @@
 # Quick Start
 To set up prerequisities and quickly deploy Intel® AI for Enterprise Inference on a single node, follow the steps in the [**Single Node Deployment Guide**](./single-node-deployment.md). Otherwise, proceed to the section below for all deployment options.
 
-> 🚀 **New**: Automated Gaudi firmware and driver management! See [Gaudi Prerequisites](./gaudi-prerequisites.md) for automated setup scripts.
+> 🚀 **New**: Automated Intel® AI Accelerator firmware and driver management! See [Intel® AI Accelerator Prerequisites](./intel-ai-accelerator-prerequisites.md) for automated setup scripts.
 
 # Complete Intel® AI for Enterprise Inference Cluster Setup
 

docs/configuring-inference-config-cfg-file.md

@@ -37,7 +37,7 @@ Make sure to update the values in the inference-config.cfg file according to you
 > - If `deploy_keycloak_apisix` is set to `off`, the `keycloak_client_id`, `keycloak_admin_user`, and `keycloak_admin_password` values will have no effect.
 > - The `hugging_face_token` is the token used for pulling LLM models from Hugging Face. 
 > - If `deploy_llm_models` is set to `off`, the `hugging_face_token` value will be ignored.
-> - The `cpu_or_gpu` value specifies whether to deploy models for CPU or Intel Gaudi.
+> - The `cpu_or_gpu` value specifies whether to deploy models for CPU or Intel® AI Accelerator.
 >
 
 For running behind corporate proxy, please refer to this [guide](./running-behind-proxy.md)

docs/cpu-optimization-guide.md

@@ -49,7 +49,7 @@ resources:
 
 For single-node Xeon clusters, **Keycloak** and **APISIX** are recommended.
 
-For Gaudi or large multi-node Xeon clusters, the GenAI Gateway is well-suited.
+For  Intel® AI Accelerator or large multi-node Xeon clusters, the GenAI Gateway is well-suited.
 
 ## Status Verification
  
@@ -74,4 +74,4 @@ If models aren't performing optimally:
 CPU optimization runs automatically and provides:
 - Dedicated CPU cores for each model
 - Consistent performance
-- Optimal resource utilization
+- Optimal resource utilization

docs/deploy-llm-model-from-hugging-face.md

@@ -17,6 +17,6 @@ This option allows you to deploy any Hugging Face-hosted LLM on the Inference Cl
 3. When prompted, provide:
    - **Hugging Face Model ID** (e.g., `meta-llama/Meta-Llama-3-8B`)  
    - **Model Deployment Name** (e.g., `metallama-8b`)  
-   - **Tensor Parallel Size** (based on available Gaudi cards)
+   - **Tensor Parallel Size** (based on available  Intel® AI Accelerator cards)
 
 > **Note**: This deploys a model that has **not** been pre-validated. Make sure the tensor parallel size is configured correctly. An incorrect value can result in the model being stuck in a "not ready" state.

docs/examples/single-node/README.md

@@ -1,16 +1,16 @@
 # Setup Single Node Using Ansible
 
-These playbooks sets up a single node inference environment on either a Intel® Gaudi or Intel® Xeon node using Ansible. It is designed to be run on the Intel® Gaudi or Intel® Xeon node where the Intel® AI for Enterprise Inference Service will be deployed. The playbooks installs all necessary dependencies, configures the environment, and prepares the system for the Intel® AI for Enterprise Inference Service. If you are going to use Intel® Gaudi, you will need to have the Gaudi drivers and firmware installed on the system before running this playbook, for more information on installing the Gaudi drivers and firmware, refer to the [Gaudi Drivers Installation Guide](https://github.com/opea-project/Enterprise-Inference/blob/main/core/catalog/docs/gaudi/gaudi-prerequisites.md).
+These playbooks sets up a single node inference environment on either a  Intel® AI Accelerator or Intel® Xeon node using Ansible. It is designed to be run on the  Intel® AI Accelerator or Intel® Xeon node where the Intel® AI for Enterprise Inference Service will be deployed. The playbooks installs all necessary dependencies, configures the environment, and prepares the system for the Intel® AI for Enterprise Inference Service. If you are going to use  Intel® AI Accelerator, you will need to have the  Intel® AI Accelerator drivers and firmware installed on the system before running this playbook, for more information on installing the Intel® AI Accelerator drivers and firmware, refer to the [Intel® AI Accelerator Drivers Installation Guide](../../intel-ai-accelerator-prerequisites.md).
 
 Many of the defaults are setup to work out of the box, but you will need to update the **`cluster_ip`** and provide the **`hf_token`** for downloading models from Hugging Face.
 
 There is also a template directory that contains a set of templates for the various configuration files that are used by the AI Inference Service. These templates are used to generate the final configuration files based on the variables defined in the playbook. Do not modify these files directly.
 
-Depending on the deployment type or the size of the models used, the playbook may run up to 25 minutes, at the end of the playbook running it will output the results of the installation script. The models will be available sometime after the playbook is done, the models selected by default for the Intel® Gaudi deployment can take up to an hour for all four of them to be available. If you change the models that will be used, the start up time may be different.
+Depending on the deployment type or the size of the models used, the playbook may run up to 25 minutes, at the end of the playbook running it will output the results of the installation script. The models will be available sometime after the playbook is done, the models selected by default for the  Intel® AI Accelerator deployment can take up to an hour for all four of them to be available. If you change the models that will be used, the start up time may be different.
 
 | Deployment Type | Playbook File |
 |------------------|----------------|
-| Gaudi Single Node Playbook | einf-singlenode-gaudi.yml |
+| Intel® AI Accelerator Single Node Playbook | einf-singlenode-intel-ai-accelerator.yml |
 | Xeon Single Node Playbook | einf-singlenode-xeon.yml |
 
 
@@ -66,12 +66,13 @@ These settings are all set to `on` by default in the playbook, change these vari
 
 2. **Run the Playbook**
 
-   Execute the Gaudi playbook using the following command:
+   Execute the  Intel® AI Accelerator playbook using the following command:
 
    ```bash
    git clone https://github.com/opea-project/Enterprise-Inference.git
    cd Enterprise-Inference/docs/examples/single-node
-   sudo ansible-playbook einf-singlenode-gaudi.yml
+   sudo ansible-playbook einf-singlenode-intel-ai-accelerator.yml
+
    ```
 
    Execute the Xeon playbook using the following command:
@@ -154,4 +155,4 @@ curl -k ${BASE_URL}/Meta-Llama-3.1-70B-Instruct/v1/completions -X POST -d '{"mod
 
 ---
 
-For more information on how to access the models, refer to the [Accessing Deployed Models](/docs/accessing-deployed-models.md) documentation.
+For more information on how to access the models, refer to the [Accessing Deployed Models](/docs/accessing-deployed-models.md) documentation.

…es/single-node/einf-singlenode-gaudi.yml …einf-singlenode-intel-ai-accelerator.ymldocs/examples/single-node/einf-singlenode-gaudi.yml renamed to docs/examples/single-node/einf-singlenode-intel-ai-accelerator.yml docs/examples/single-node/einf-singlenode-gaudi.yml renamed to docs/examples/single-node/einf-singlenode-intel-ai-accelerator.yml

@@ -1,7 +1,7 @@
 # Copyright (C) 2025-2026 Intel Corporation
 # SPDX-License-Identifier: Apache-2.0
 
-# Ansible Playbook to install and configure the Enterprise Inference Service on a Single Gaudi node running Ubuntu 22.04+
+# Ansible Playbook to install and configure the Enterprise Inference Service on a Single node of Intel® AI Accelerator running Ubuntu 22.04+
 # Needs to run as root or with sudo privileges
 # Installs version:
 ---
@@ -11,7 +11,7 @@
   gather_facts: true
   vars:
     cluster_url: "api.example.com" # Cluster name, change if you want to use a different DNS name for the service
-    cluster_ip: "127.0.0.1" # Cluster IP, this should be the IP of the Gaudi node that will be used to access the service
+    cluster_ip: "127.0.0.1" # Cluster IP, this should be the IP of the node that will be used to access the service
     ai_user: "ai-inference" # Enterprise Inference Service OS user, change if you want to use a different user
     ssh_key_file: "/home/{{ ai_user }}/.ssh/id_rsa" # Path to your private key, this playbook will create this
     keycloak_client_id: "api" # Keycloak client ID
@@ -20,7 +20,7 @@
     hf_token: "YourHuggingFaceToken" # Hugging Face token for all models, you need to supply your Hugging Face token to download models
     hf_token_falcon3: "YourHuggingFaceToken" # Hugging Face token for Falcon 3, can be the same as hf_token
     models: "2,5,8,9" # Comma-separated list of model IDs, see repo
-    cpu_or_gpu: "gpu" # "cpu" or "gpu", set to "gpu" for Gaudi nodes
+    cpu_or_gpu: "gpu" # "cpu" or "gpu", set to "gpu" for Intel® AI Accelerator nodes
     deploy_kubernetes_fresh: "on"
     deploy_ingress_controller: "on"
     deploy_keycloak_apisix: "on"

docs/examples/single-node/einf-singlenode-xeon.yml

@@ -11,7 +11,7 @@
   gather_facts: true
   vars:
     cluster_url: "api.example.com"                        # Cluster name, change if you want to use a different DNS name for the service
-    cluster_ip: "127.0.0.1"                               # Cluster IP, this should be the IP of the Gaudi node that will be used to access the service
+    cluster_ip: "127.0.0.1"                               # Cluster IP, this should be the IP of the Intel® AI Accelerator node that will be used to access the service
     ai_user: "ai-inference"                               # Enterprise Inference Service OS user, change if you want to use a different user
     ssh_key_file: "/home/{{ ai_user }}/.ssh/id_rsa"       # Path to your private key, this playbook will create this
     keycloak_client_id: "api"                             # Keycloak client ID
@@ -20,7 +20,7 @@
     hf_token: "YourHuggingFaceToken"                      # Hugging Face token for all models, you need to supply your Hugging Face token to download models
     hf_token_falcon3: "YourHuggingFaceToken"              # Hugging Face token for Falcon 3, can be the same as hf_token
     models: "21"                                          # Comma-separated list of model IDs, see repo
-    cpu_or_gpu: "cpu"                                     # "cpu" or "gpu", set to "gpu" for Gaudi nodes
+    cpu_or_gpu: "cpu"                                     # "cpu" or "gpu", set to "gpu" for Intel® AI Accelerator nodes
     deploy_kubernetes_fresh: "on"
     deploy_ingress_controller: "on"
     deploy_keycloak_apisix: "on"

docs/gaudi-prerequisites.md …cs/intel-ai-accelerator-prerequisites.mddocs/gaudi-prerequisites.md renamed to docs/intel-ai-accelerator-prerequisites.md docs/gaudi-prerequisites.md renamed to docs/intel-ai-accelerator-prerequisites.md

@@ -1,9 +1,9 @@
-# Gaudi Node Requirements and Setup Guide
+# Intel® AI Accelerator Node Requirements and Setup Guide
 
-This guide helps verify and automatically install the latest firmware and driver version for **Habana Gaudi** nodes in your Kubernetes or Standalone Environment.
+This guide helps verify and automatically install the latest firmware and driver version for **Intel® AI Accelerator** nodes in your Kubernetes or Standalone Environment.
 
 # What You Need
-- Intel® Gaudi® cards installed in your system 
+- Intel® AI Accelerator cards installed in your system 
 - Linux operating system
 - Internet connection
 - Root/sudo privileges
@@ -33,11 +33,11 @@ Firmware [SPI] Version : Preboot version hl-gaudi2-1.20.0-fw-58.0.0-sec-9 (Jan 1
 ```
 ###### For visual assistance, refer to the following snapshot for Firmware version:
 
-<img src="../docs/pictures/Enterprise-Inference-Gaudi-Firmware-version.png" alt="AI Inference Firmware Snapshot" width="800" height="120"/>   
+<img src="../docs/pictures/Enterprise-Inference-Intel-AI-Accelerator-Firmware-version.png" alt="AI Inference Firmware Snapshot" width="800" height="120"/>   
 
 
 #### Step 2: Check Driver Version
-Use the following commands to check the required driver version installed on your Gaudi nodes:
+Use the following commands to check the required driver version installed on your Intel® AI Accelerator nodes:
 
 ```bash
 hl-smi 
@@ -52,7 +52,7 @@ You'll see something like:
 ```
 ###### For visual assistance, refer to the following snapshot for Driver version:
 
-<img src="../docs/pictures/Enterprise-Inference-Gaudi-Driver-version.png" alt="AI Inference Driver Snapshot" width="800" height="120"/>    
+<img src="../docs/pictures/Enterprise-Inference-Intel-AI-Accelerator-Driver-version.png" alt="AI Inference Driver Snapshot" width="800" height="120"/>    
 
 #### Step 3: Check Runtime Version
 
@@ -126,7 +126,7 @@ If the numbers don't match, run:
 ```bash
 kubectl rollout restart ds habana-ai-device-plugin-ds -n habana-ai-operator
 ```
-> **For detailed documentation, refer to the official guide:** [Intel® Gaudi® Software Installation Documentation](https://docs.habana.ai/en/latest/Installation_Guide/Driver_Installation.html)
+> **For detailed documentation, refer to the official guide:** [Intel® AI Accelerator Software Installation Documentation](https://docs.habana.ai/en/latest/Installation_Guide/Driver_Installation.html)
 >
 > **For automation script details:** See [Firmware Update Script Documentation](../core/scripts/README.md)
 >