Fix A100/H100 profiles, add examples + GitHub Pages docs, exclude toy_models from distribution, prep for PyPI

.github/workflows/docs.yml

@@ -0,0 +1,47 @@
+name: docs
+
+on:
+  push:
+    branches: [main, polish-ecal-package]
+  pull_request:
+  workflow_dispatch:
+
+permissions:
+  contents: read
+
+jobs:
+  build:
+    runs-on: ubuntu-latest
+    steps:
+      - uses: actions/checkout@v4
+
+      - uses: actions/setup-python@v5
+        with:
+          python-version: "3.11"
+          cache: pip
+
+      - name: Install package with docs extras
+        run: pip install -e ".[docs]"
+
+      - name: Build Sphinx docs
+        run: sphinx-build -b html -W --keep-going docs docs/_build/html
+
+      - name: Upload docs artifact
+        uses: actions/upload-pages-artifact@v3
+        with:
+          path: docs/_build/html
+
+  deploy:
+    if: github.event_name == 'workflow_dispatch' || (github.event_name == 'push' && (github.ref == 'refs/heads/main' || github.ref == 'refs/heads/polish-ecal-package'))
+    needs: build
+    runs-on: ubuntu-latest
+    permissions:
+      pages: write
+      id-token: write
+    environment:
+      name: github-pages
+      url: ${{ steps.deployment.outputs.page_url }}
+    steps:
+      - name: Deploy to GitHub Pages
+        id: deployment
+        uses: actions/deploy-pages@v4

MANIFEST.in

@@ -0,0 +1,2 @@
+recursive-include tests *.py
+recursive-include src/ecal/hardware/data *.yaml

README.md

@@ -6,6 +6,8 @@ eCAL computes the total energy consumed across the full AI model lifecycle — d
 
 Published in **IEEE Journal on Selected Areas in Communications (JSAC), 2026**.
 
+[Documentation](https://vh2001.github.io/eCAL/)
+
 ## Installation
 
 ### From source (recommended for development)
@@ -84,7 +86,7 @@ python RunCalculator.py
 | Profile            | FP32 FLOPS   | TDP (W) | Device |
 |--------------------|-------------|---------|--------|
 | `apple_m2`         | 3.6 TFLOPS  | 22      | mps    |
-| `nvidia_a100_80gb` | 19.5 TFLOPS | 300     | cuda   |
+| `nvidia_a100_80gb` | 19.5 TFLOPS | 400     | cuda   |
 | `nvidia_h100_sxm`  | 67 TFLOPS   | 700     | cuda   |
 | `generic_cpu`      | 1 TFLOPS    | 100     | cpu    |
 | `generic_edge`     | 0.01 TFLOPS | 15      | cpu    |