Kade Heckel

Here's a paper being presented at the Next-Generation Sequence Modeling Workshop at ICML next week: https://arxiv.org/abs/2406.09477 The takeaway is that for quantization aware training and inference on LRA, most parameters...

This is tied to the implementation of latency based training tools/objectives. #21

See docs/examples/nir for notebooks documenting functionality and testing. Currently works for single neuron loading example, writing the model back is a work in progress.

Working on getting the weight scaling to function properly. - [x] Get weight scaling working so that loaded models function properly

Importing models is now supported but is likely somewhat brittle. Will require further testing. Export capabilities started but limited to FFN for now, rest is a work in progress.

This needs formal tests included into the library before closing this issue.

https://arxiv.org/abs/2401.00955 Spiking State Space Machine Paper.

A prototype implementation has been implemented in spyx.experimental. Need to verify the dimensions of internal calculation as right now there's broadcasting issues if the output dimension isn't a multiple/fraction of...

Found this: Parallel Spiking Unit: https://arxiv.org/abs/2402.00449

https://docs.taichi-lang.org/ Taichi might be another great option for including enhanced/high performance kernels into the system?