SetFloat32MatmulPrecision

Sets internal precision for float32 matrix multiplications.

Abstract Signature:

SetFloat32MatmulPrecision(precision: str)

PyTorchJAX (Core)

PyTorch

API: torch.set_float32_matmul_precision

Strategy: Direct Mapping

Official Docs ↗

JAX (Core)

API: —

Strategy: Macro 'jax.config.update('jax_default_matmul_precision', {precision})'