cld2labs/Qwen3-8b (#91)

* feat: add Qwen3-8B model card and deployment guide for Dell EI

Signed-off-by: arpannookala-12 <ganesh.arpan.nookala@cloud2labs.com>

* update qwen3-8b deployment.md

* Remove README.md from model-deployment folder

---------

Signed-off-by: arpannookala-12 <ganesh.arpan.nookala@cloud2labs.com>
Co-authored-by: Harika <codewith3@gmail.com>

Author: arpannookala-12

third_party/Dell/model-deployment/Qwen3-8b/deployment.md

@@ -0,0 +1,101 @@
+## Step 1: Prerequisites to Deploy Qwen3-8b Model on Xeon with Keycloak
+
+Ensure the Enterprise Inference stack with Keycloak is already deployed before proceeding.
+
+Edit `core/scripts/generate-token.sh` and set your values before sourcing it:
+
+| Variable                  | Description                                                              |
+| ------------------------- | ------------------------------------------------------------------------ |
+| `BASE_URL`                | Hostname of your cluster (e.g. `api.example.com`), without `https://`   |
+| `KEYCLOAK_ADMIN_USERNAME` | Keycloak admin username                                                  |
+| `KEYCLOAK_PASSWORD`       | Keycloak admin password                                                  |
+| `KEYCLOAK_CLIENT_ID`      | Keycloak client ID configured during EI deployment                       |
+
+Then run:
+
+```bash
+export HUGGING_FACE_HUB_TOKEN="your_token_here"
+
+cd ~/Enterprise-Inference
+source core/scripts/generate-token.sh
+```
+
+This exports: `BASE_URL`, `KEYCLOAK_CLIENT_ID`, `KEYCLOAK_CLIENT_SECRET`, and `TOKEN`.
+
+## Step 2: Deploy Qwen3-8b Model
+
+```bash
+helm install qwen3-8b-cpu ./core/helm-charts/vllm \
+  --values ./core/helm-charts/vllm/xeon-values.yaml \
+  --set LLM_MODEL_ID="Qwen/Qwen3-8B" \
+  --set global.HUGGINGFACEHUB_API_TOKEN="$HUGGING_FACE_HUB_TOKEN" \
+  --set ingress.enabled=true \
+  --set ingress.secretname="${BASE_URL}" \
+  --set ingress.host="${BASE_URL}" \
+  --set oidc.client_id="$KEYCLOAK_CLIENT_ID" \
+  --set oidc.client_secret="$KEYCLOAK_CLIENT_SECRET" \
+  --set apisix.enabled=true \
+  --set tensor_parallel_size="1" \
+  --set pipeline_parallel_size="1"
+```
+
+## Step 3: Verify the Deployment
+
+```bash
+kubectl get pods
+kubectl get apisixroutes
+```
+
+Expected Output:
+
+```
+NAME                                    READY   STATUS    RESTARTS
+keycloak-0                              1/1     Running   0
+keycloak-postgresql-0                   1/1     Running   0
+qwen3-8b-cpu-vllm-<hash>-<hash>         1/1     Running   0
+```
+
+> Note: The pod name suffix `<hash>-<hash>` is auto-generated by Kubernetes and will differ on each deployment. Ensure all pods show `1/1 Running`.
+
+```
+NAME                           HOSTS
+qwen3-8b-cpu-vllm-apisixroute  api.example.com
+```
+
+## Step 4: Test the Deployed Model
+
+```bash
+curl -k https://${BASE_URL}/Qwen3-8B-vllmcpu/v1/completions \
+  -X POST \
+  -H "Content-Type: application/json" \
+  -H "Authorization: Bearer $TOKEN" \
+  -d '{
+    "model": "Qwen/Qwen3-8B",
+    "prompt": "What is Deep Learning?",
+    "max_tokens": 25,
+    "temperature": 0
+  }'
+```
+
+If successful, the model will return a completion response.
+
+## To undeploy the model
+
+```bash
+helm uninstall qwen3-8b-cpu
+```
+
+## Parameters
+
+| Parameter                                       | Description                                                                                       |
+| ----------------------------------------------- | ------------------------------------------------------------------------------------------------- |
+| `--set LLM_MODEL_ID="Qwen/Qwen3-8B"`            | Defines the target model from **Hugging Face** to deploy.                                         |
+| `--set global.HUGGINGFACEHUB_API_TOKEN="..."`   | Authenticates access to gated or private Hugging Face models. Replace with your own secure token. |
+| `--set ingress.enabled=true`                    | Enables Kubernetes **Ingress** to expose the model service externally.                            |
+| `--set ingress.host="${BASE_URL}"`              | Public hostname or FQDN for the inference endpoint (maps to your Ingress controller IP).          |
+| `--set ingress.secretname="${BASE_URL}"`        | Kubernetes **TLS Secret** used for HTTPS termination at the ingress layer.                        |
+| `--set oidc.client_id="..."`                    | Keycloak OIDC client ID used for token-based authentication.                                      |
+| `--set oidc.client_secret="..."`                | Keycloak OIDC client secret corresponding to the client ID.                                       |
+| `--set apisix.enabled=true`                     | Enables **APISIX** as the API gateway for routing and authentication.                             |
+| `--set tensor_parallel_size="1"`                | Number of tensor parallel workers. Set to the number of available CPUs/GPUs per node.            |
+| `--set pipeline_parallel_size="1"`              | Number of pipeline parallel stages. Typically `1` for single-node deployments.                   |

third_party/Dell/model-deployment/Qwen3-8b/model-card.md

@@ -0,0 +1,62 @@
+# Qwen3-8B
+
+This model uses Qwen3-8B, a large-scale open-weight language model developed by the Qwen Team at Alibaba Cloud. It is designed for high-quality natural language understanding, reasoning, instruction following, and code intelligence across a broad range of enterprise and research workloads. Qwen3-8B represents the next-generation evolution of the Qwen model family, with improved reasoning depth, instruction alignment, and multilingual capabilities.
+
+For full details including model specifications, licensing, intended use, safety guidance, and example prompts, please visit the official Hugging Face page: **Official Hugging Face Page**
+
+https://huggingface.co/Qwen/Qwen3-8B
+
+This model provides inference services only; weights are hosted by Hugging Face under the Qwen License.
+
+Ensure compliance with the Qwen License terms before using this model.
+
+### Model Attribution
+
+**Developer:**	Alibaba Cloud / Qwen Team
+
+**purpose:** General-purpose instruction-tuned reasoning and language model
+
+**Sizes/Variants:**	8B parameters
+
+**Modalities:**	Text → Natural Language + Code
+
+**Parameter Size:** 8 Billion
+
+**Max Context:**	Up to ~128K tokens (depending on backend integration)
+
+**License:** Qwen License (commercial use permitted with conditions)
+
+### Usage Notice
+
+**By using this model, you agree that:**
+
+- Inputs and outputs are processed by the Qwen3-8B model under the Qwen License.
+- You are responsible for validating outputs before production use.
+- This model should not be used for generating malicious, deceptive, or unsafe content.
+- Commercial usage must comply with all Qwen license obligations and regional legal requirements..
+
+### Intended Applications
+
+- Enterprise chatbots and virtual assistants
+- Retrieval-Augmented Generation (RAG) systems
+- Agentic AI workflows and task automation
+- Code generation, debugging, and refactoring
+- API reasoning and architecture guidance
+- Multilingual document analysis and summarization
+- Knowledge base and search augmentation systems
+
+### Limitations
+
+- Higher compute and memory requirements than sub-3B models
+- May hallucinate in open-ended or low-context prompts
+- Not suitable for unsupervised safety-critical decision systems
+- Long-context performance depends on serving backend configuration
+- Requires responsible deployment with output validation
+
+### References
+
+Qwen Project Official Repository - https://github.com/QwenLM
+
+Hugging Face Model Page — https://huggingface.co/Qwen/Qwen3-8B
+
+Qwen License - https://github.com/QwenLM/Qwen/blob/main/LICENSE