Add custom CUDA kernels to README (#71)

README.md

@@ -154,7 +154,8 @@ Thunder doesn't generate code for accelerators directly. It acquires and transfo
 - [Apex](https://github.com/NVIDIA/apex)
 - [TransformerEngine](https://github.com/NVIDIA/TransformerEngine)
 - [PyTorch eager](https://github.com/pytorch/pytorch)
-- custom kernels, including those written with [OpenAI Triton](https://github.com/openai/triton)
+- Custom CUDA kernels through [PyCUDA](https://documen.tician.de/pycuda/tutorial.html#interoperability-with-other-libraries-using-the-cuda-array-interface), [Numba](https://numba.readthedocs.io/en/stable/cuda/kernels.html), [CuPy](https://docs.cupy.dev/en/stable/user_guide/kernel.html)
+- Custom kernels written in [OpenAI Triton](https://github.com/openai/triton)
 
 Modules and functions compiled with Thunder fully interoperate with vanilla PyTorch and support PyTorch's autograd. Also, Thunder works alongside torch.compile to leverage its state-of-the-art optimizations.
 

pyproject.toml

@@ -56,7 +56,8 @@ quiet-level = 3
 #  https://github.com/codespell-project/codespell/issues/2839#issuecomment-1731601603
 # also adding links until they ignored by its: nature
 #  https://github.com/codespell-project/codespell/issues/2243#issuecomment-1732019960
-#ignore-words-list = ""
+# documen is used in an url in README
+ignore-words-list = "documen"
 
 
 [tool.black]