module

transport.samples.kernels.cg_python_batched

module torchmatch.transport.samples.kernels.cg_python_batched

Python-level batched CG for HVP acceleration.

This module implements a batched CG solver that uses the apply_plan_vec_shifted kernels for improved performance and reduced memory usage. This avoids the mysterious Triton compilation state issues observed with the fully-inline batched CG kernel while still providing a clean interface for batched CG solving. Includes a torch.compile-compatible version for additional speedup.

Members

type

function

Source: torchmatch/transport/samples/kernels/cg_python_batched.py:1