[decitre]

ch13_webgpu.ipynb shows that WebGPU inference really runs on the GPU: the
hardware adapter, model tensors held in GPU memory, and WebGPU vs WASM timing
for the same greedy generation with SmolLM2-135M-Instruct (q4). Link it from
the README and the ch01 introduction, and cover it in the notebook tests with
stubbed adapter and tensor-location probes.

[codecov]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 82.96%. Comparing base (1285278) to head (16096aa).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@           Coverage Diff           @@
##             main      #10   +/-   ##
=======================================
  Coverage   82.96%   82.96%           
=======================================
  Files           8        8           
  Lines        2472     2472           
=======================================
  Hits         2051     2051           
  Misses        421      421           

Flag	Coverage Δ
javascript	79.19% <ø> (ø)
python	87.81% <ø> (ø)

Flags with carried forward coverage won't be shown. Click here to find out more.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.
• 📦 JS Bundle Analysis: Save yourself from yourself by tracking and limiting bundle sizes in JS merges.