Qqmm ==== Quantized Matrix Multiplication. **Abstract Signature:** ``Qqmm(x: Tensor, w: Tensor, scales: Tensor | None, group_size: int | None, bits: int | None, mode: str = nvfp4)`` .. raw:: html

PyTorch

API:
Strategy: Plugin (quantized_matmul)

JAX (Core)

API:
Strategy: Plugin (quantized_matmul)

Keras

API:
Strategy: Plugin (quantized_matmul)

TensorFlow

API:
Strategy: Plugin (quantized_matmul)

Apple MLX

API: mlx.core.qqmm
Strategy: Direct Mapping

Flax NNX

API:
Strategy: Plugin (quantized_matmul)

PaxML / Praxis

API:
Strategy: Plugin (quantized_matmul)