Hello, I’m working on a circuit to train one weight per input. At first, I used default.qubit, sending a batch of inputs and weights to be trained each circuit call. This is deemed to be slow (1.5s per epoch for batch size 512) and memory hungry, with a batch size of 512 requiring 29 GB. I switched…

Lightning gpu batch circuit

Ahmed_Fourati May 8, 2025, 11:04pm 5

Heyy,

Multiplying the wires is an idea shared here Backprop for Lightning.gpu.

Can you send me more about broadcasting, please? I can only find deprecated documentation on pennylane.

Best,

Topic		Replies	Views
Batching Inputs to Quantum Circuit PennyLane Help	14	3282	September 10, 2019
Pennylane lightning.gpu, 28+ qubits quantum circuit PennyLane Help	20	2269	March 16, 2023
Lightning.gpu taking longer time w.r.t circuit depth PennyLane Help	7	454	March 23, 2023
Question on data parallelization PennyLane Help	4	483	January 24, 2024
Pytorch backpropagation RAM issue PennyLane Help	9	955	March 16, 2021