Addmm

Performs a matrix multiplication of the matrices mat1 and mat2. The matrix input is added to the final result.

Abstract Signature:

Addmm(input: Tensor, mat1: Tensor, mat2: Tensor, beta: float = 1.0, alpha: float = 1.0)

PyTorchJAX (Core)NumPyKerasTensorFlowApple MLXFlax NNXPaxML / Praxis

PyTorch

API: torch.addmm

Strategy: Direct Mapping

Official Docs ↗

JAX (Core)

API: —

Strategy: Macro 'jnp.add({beta} * {input}, {alpha} * jnp.matmul({mat1}, {mat2}))'

NumPy

API: —

Strategy: Macro '{beta} * {input} + {alpha} * np.matmul({mat1}, {mat2})'

Keras

API: —

Strategy: Macro 'keras.ops.add({beta} * {input}, {alpha} * keras.ops.matmul({mat1}, {mat2}))'

TensorFlow

API: —

Strategy: Macro 'tf.math.add({beta} * {input}, {alpha} * tf.linalg.matmul({mat1}, {mat2}))'

Apple MLX

API: mlx.core.addmm

Strategy: Macro 'mx.add({beta} * {input}, {alpha} * mx.matmul({mat1}, {mat2}))'

Flax NNX

API: —

Strategy: Macro 'jnp.add({beta} * {input}, {alpha} * jnp.matmul({mat1}, {mat2}))'

PaxML / Praxis

API: —

Strategy: Macro 'jnp.add({beta} * {input}, {alpha} * jnp.matmul({mat1}, {mat2}))'