Pure and transparent
Trace every operation from Python to the C++ core. Peel back each abstraction and keep the full path readable.
SEE THE SYSTEM.CHANGE IT.
Trace every tensor to its kernel. A PyTorch-compatible framework for learning, research, and hardware experiments.
No hidden compute path. Read, verify, and recompose every forward pass, gradient, and kernel execution.
01Forward pass
02Autograd
03Kernel execution
Clarity beats magic.
DIY acceleration
Readable CPU and CUDA backends leave room for custom kernels, new hardware, and nanobind experiments.
Modular autograd
TPX decouples computation from gradients, making dynamic graphs and new differentiation modes easier to modify.
Research ready
Prototype layers, optimizers, storage formats, operator fusion, and static graph capture with less boilerplate.
Four layers. No black box.
Execute
The pure tensor engine for memory, kernels, dispatch, and hardware backends.
Trace
The explicit autograd layer for dynamic graphs, gradients, and backward execution.
Accelerate
The static graph and JIT playground for fusion, capture, and compute optimization.
Build
The PyTorch-compatible neural network layer, from Linear and Conv2d to custom modules.
Run it. Then open it.
Choose an environment and copy the command. The full compute path is ready to inspect.
python3 -m pip install tensorplay --upgradeDispatches from inside the system.
Keep going.
Open the black box with us.
Students, developers, educators, and researchers are welcome. Learn the system, contribute code, discuss architecture, or follow project updates.