2nd POC for How to Use ROCm for AI (#282) (#4299)

* New TOC for ROCm for AI developed

Co-authored-by: Peter Park <peter.park@amd.com>

docs/sphinx/_toc.yml.in

@@ -36,40 +36,62 @@ subtrees:
     title: Use ROCm for AI
     subtrees:
     - entries:
-      - file: how-to/rocm-for-ai/install.rst
-        title: Installation
-      - file: how-to/rocm-for-ai/train-a-model.rst
-        title: Train a model
-      - file: how-to/rocm-for-ai/scale-model-training.rst
-        title: Scale model training
-      - file: how-to/rocm-for-ai/hugging-face-models.rst
-        title: Run models from Hugging Face
-      - file: how-to/rocm-for-ai/deploy-your-model.rst
-        title: Deploy your model
-  - file: how-to/rocm-for-hpc/index.rst
-    title: Use ROCm for HPC
-  - file: how-to/llm-fine-tuning-optimization/index.rst
-    title: Fine-tune LLMs and inference optimization
-    subtrees:
-    - entries:
-      - file: how-to/llm-fine-tuning-optimization/overview.rst
-        title: Conceptual overview
-      - file: how-to/llm-fine-tuning-optimization/fine-tuning-and-inference.rst
+      - file: how-to/rocm-for-ai/training/index.rst
+        title: Training
         subtrees:
         - entries:
-          - file: how-to/llm-fine-tuning-optimization/single-gpu-fine-tuning-and-inference.rst
-            title: Use a single accelerator
-          - file: how-to/llm-fine-tuning-optimization/multi-gpu-fine-tuning-and-inference.rst
-            title: Use multiple accelerators
-      - file: how-to/llm-fine-tuning-optimization/model-quantization.rst
-      - file: how-to/llm-fine-tuning-optimization/model-acceleration-libraries.rst
-      - file: how-to/llm-fine-tuning-optimization/llm-inference-frameworks.rst
-      - file: how-to/llm-fine-tuning-optimization/optimizing-with-composable-kernel.md
-        title: Optimize with Composable Kernel
-      - file: how-to/llm-fine-tuning-optimization/optimizing-triton-kernel.rst
-        title: Optimize Triton kernels
-      - file: how-to/llm-fine-tuning-optimization/profiling-and-debugging.rst
-        title: Profile and debug
+          - file: how-to/rocm-for-ai/training/train-a-model.rst
+            title: Train a model
+          - file: how-to/rocm-for-ai/training/scale-model-training.rst
+            title: Scale model training
+      
+      - file: how-to/rocm-for-ai/fine-tuning/index.rst
+        title: Fine-tuning LLMs
+        subtrees:
+        - entries:
+          - file: how-to/rocm-for-ai/fine-tuning/overview.rst
+            title: Conceptual overview
+          - file: how-to/rocm-for-ai/fine-tuning/fine-tuning-and-inference.rst
+            title: Fine-tuning
+            subtrees:
+            - entries:
+              - file: how-to/rocm-for-ai/fine-tuning/single-gpu-fine-tuning-and-inference.rst
+                title: Use a single accelerator
+              - file: how-to/rocm-for-ai/fine-tuning/multi-gpu-fine-tuning-and-inference.rst
+                title: Use multiple accelerators
+
+      - file: how-to/rocm-for-ai/inference/index.rst
+        title: Inference
+        subtrees:
+        - entries:
+          - file: how-to/rocm-for-ai/inference/install.rst
+            title: Installation
+          - file: how-to/rocm-for-ai/inference/hugging-face-models.rst
+            title: Run models from Hugging Face
+          - file: how-to/rocm-for-ai/inference/llm-inference-frameworks.rst
+            title: LLM inference frameworks
+          - file: how-to/rocm-for-ai/inference/vllm-benchmark.rst
+            title: Performance validation
+          - file: how-to/rocm-for-ai/inference/deploy-your-model.rst
+            title: Deploy your model
+
+      - file: how-to/rocm-for-ai/inference-optimization/index.rst
+        title: Inference optimization
+        subtrees:
+        - entries:
+          - file: how-to/rocm-for-ai/inference-optimization/model-quantization.rst
+          - file: how-to/rocm-for-ai/inference-optimization/model-acceleration-libraries.rst
+          - file: how-to/rocm-for-ai/inference-optimization/optimizing-with-composable-kernel.md
+            title: Optimize with Composable Kernel
+          - file: how-to/rocm-for-ai/inference-optimization/optimizing-triton-kernel.rst
+            title: Optimize Triton kernels
+          - file: how-to/rocm-for-ai/inference-optimization/profiling-and-debugging.rst
+            title: Profile and debug
+          - file: how-to/rocm-for-ai/inference-optimization/workload.rst
+            title: Workload tuning
+  
+  - file: how-to/rocm-for-hpc/index.rst
+    title: Use ROCm for HPC
   - file: how-to/system-optimization/index.rst
     title: System optimization
     subtrees:
@@ -86,14 +108,6 @@ subtrees:
         title: AMD RDNA 2
   - file: how-to/tuning-guides/mi300x/index.rst
     title: AMD MI300X performance validation and tuning
-    subtrees:
-    - entries:
-      - file: how-to/performance-validation/mi300x/vllm-benchmark.rst
-        title: Performance validation
-      - file: how-to/tuning-guides/mi300x/system.rst
-        title: System tuning
-      - file: how-to/tuning-guides/mi300x/workload.rst
-        title: Workload tuning
   - file: how-to/system-debugging.md
   - file: conceptual/compiler-topics.md
     title: Use advanced compiler features