feat: add CNCF AI Conformance evidence collection framework

Add evidence collection script and test manifests for CNCF AI Conformance
Must-have requirements (Kubernetes v1.34). The script collects structured
markdown evidence for 6 feature areas: DRA support, gang scheduling,
secure accelerator access, accelerator metrics, inference gateway, and
robust AI operator.

Evidence demonstrates that a cluster configured with the
h100-eks-ubuntu-inference-dynamo recipe meets conformance requirements.

Signed-off-by: Yuan Chen <yuanchen97@gmail.com>

Author: yuanchen8911

.github/workflows/gpu-h100-smoke-test.yaml

@@ -29,6 +29,7 @@ on:
       - '.github/actions/load-versions/**'
       - 'tests/manifests/**'
       - 'tests/chainsaw/ai-conformance/**'
+      - 'docs/conformance/cncf/**'
       - 'recipes/components/dynamo-platform/**'
       - 'recipes/overlays/kind.yaml'
       - 'recipes/overlays/kind-inference.yaml'
@@ -193,7 +194,7 @@ jobs:
       - name: Deploy DRA GPU test
         run: |
           kubectl --context="kind-${KIND_CLUSTER_NAME}" apply \
-            -f tests/manifests/dra-gpu-test.yaml
+            -f docs/conformance/cncf/manifests/dra-gpu-test.yaml
 
           echo "Waiting for DRA GPU test pod to complete..."
           if kubectl --context="kind-${KIND_CLUSTER_NAME}" -n dra-test \
@@ -216,7 +217,7 @@ jobs:
         if: always()
         run: |
           kubectl --context="kind-${KIND_CLUSTER_NAME}" delete \
-            -f tests/manifests/dra-gpu-test.yaml --ignore-not-found 2>/dev/null || true
+            -f docs/conformance/cncf/manifests/dra-gpu-test.yaml --ignore-not-found 2>/dev/null || true
 
       # --- Evidence collection ---
 

docs/conformance/cncf/README.md

@@ -0,0 +1,69 @@
+# CNCF AI Conformance Evidence
+
+## Overview
+
+This directory contains evidence for [CNCF Kubernetes AI Conformance](https://github.com/cncf/k8s-ai-conformance)
+certification. The evidence demonstrates that a cluster configured with a specific
+recipe meets the Must-have requirements for Kubernetes v1.34.
+
+> **Note:** It is the **cluster configured by a recipe** that is conformant, not the
+> tool itself. The recipe determines which components are deployed and how they are
+> configured. Different recipes may produce clusters with different conformance profiles.
+
+**Recipe used:** `h100-eks-ubuntu-inference-dynamo`
+**Cluster:** EKS with p5.48xlarge (8x NVIDIA H100 80GB HBM3)
+**Kubernetes:** v1.34
+
+## Directory Structure
+
+```
+docs/conformance/cncf/
+├── README.md
+├── collect-evidence.sh
+├── manifests/
+│   ├── dra-gpu-test.yaml
+│   └── gang-scheduling-test.yaml
+└── evidence/
+    ├── index.md
+    ├── dra-support.md
+    ├── gang-scheduling.md
+    ├── secure-accelerator-access.md
+    ├── accelerator-metrics.md
+    ├── inference-gateway.md
+    └── robust-operator.md
+```
+
+## Usage
+
+```bash
+# Collect all evidence
+./docs/conformance/cncf/collect-evidence.sh all
+
+# Collect evidence for a single feature
+./docs/conformance/cncf/collect-evidence.sh dra
+./docs/conformance/cncf/collect-evidence.sh gang
+./docs/conformance/cncf/collect-evidence.sh secure
+./docs/conformance/cncf/collect-evidence.sh metrics
+./docs/conformance/cncf/collect-evidence.sh gateway
+./docs/conformance/cncf/collect-evidence.sh operator
+```
+
+## Evidence
+
+See [evidence/index.md](evidence/index.md) for a summary of all collected evidence and results.
+
+## Feature Areas
+
+| # | Feature | Requirement | Evidence File |
+|---|---------|-------------|---------------|
+| 1 | DRA Support | `dra_support` | [evidence/dra-support.md](evidence/dra-support.md) |
+| 2 | Gang Scheduling | `gang_scheduling` | [evidence/gang-scheduling.md](evidence/gang-scheduling.md) |
+| 3 | Secure Accelerator Access | `secure_accelerator_access` | [evidence/secure-accelerator-access.md](evidence/secure-accelerator-access.md) |
+| 4 | Accelerator & AI Service Metrics | `accelerator_metrics`, `ai_service_metrics` | [evidence/accelerator-metrics.md](evidence/accelerator-metrics.md) |
+| 5 | Inference API Gateway | `ai_inference` | [evidence/inference-gateway.md](evidence/inference-gateway.md) |
+| 6 | Robust AI Operator | `robust_controller` | [evidence/robust-operator.md](evidence/robust-operator.md) |
+
+## TODO
+
+- [ ] **Cluster Autoscaling** (`cluster_autoscaling`, MUST) — Demonstrate Karpenter or cluster autoscaler scaling GPU node groups based on pending pod requests
+- [ ] **Pod Autoscaling** (`pod_autoscaling`, MUST) — Demonstrate HPA scaling pods based on custom GPU metrics (e.g., `gpu_utilization` from prometheus-adapter)