Solving poker in custom WebGPU kernels

I wanted to build a poker solver that I could host for ~free. This meant running client-side, where the best browser technology is WebGPU. The tensor library I wanted did not exist, but in the LLM era we sometimes don't need libraries at all. I had Codex turn my thousands of lines of PyTorch code into custom WebGPU kernels with parity tests. Codex then spent days optimizing those kernels.You can use the solver at https://holdem.computer, and the source is at https://github.com/phulin/poker2.