Intra-layer mixed precision quantization for neural networks

A system comprising:

• a neural network accelerator apparatus comprising:
• one or more processors;
• and
• one or more computer-readable media storing processor executable instructions which, when executed using the one or more processors, perform operations comprising:
• determining, for a first layer of a neural network, a first tensor wherein the first tensor comprises a plurality of rows;
• selecting, from the first tensor, a first set of rows from among the plurality of rows;
• selecting, from the first tensor, a second set of rows from among the plurality of rows;
• selecting, for the first set of rows, a first quantization algorithm associated with a first bitwidth;
• selecting, for the second set of rows, a second quantization algorithm associated with a second bitwidth;
• generating, a quantized first tensor by quantizing values of the first set of rows using the first quantization algorithm and quantizing values of the second set of rows using the second quantization algorithm;
• and
• computing an output for a second layer of the neural network using the quantized first tensor.

A method comprising:

• computing, for a first layer of a neural network, a first tensor wherein the first tensor comprises a plurality of rows;
• selecting, from the first tensor, a first set of rows from among the plurality of rows;
• selecting, from the first tensor, a second set of rows from among the plurality of rows;
• selecting, for the first set of rows, a first quantization algorithm associated with a first bitwidth;
• selecting, for the second set of rows, a second quantization algorithm associated with a second bitwidth;
• generating, a quantized first tensor by quantizing values of the first set of rows using the first quantization algorithm and quantizing values of the second set of rows using the second quantization algorithm;
• and
• computing an output for a second layer of the neural network using the quantized first tensor.