search

NeuroBench / neurobench

Benchmark harness and baseline results for the NeuroBench algorithm track.
https://neurobench.readthedocs.io
Apache License 2.0
52 stars 12 forks source link

Connection Sparsity with torch QuantizedLinear #229

Open jasonlyik opened 1 month ago

jasonlyik commented 1 month ago

Add torch QuantizedLinear as recognized class in connection_sparsity metric, should be another case in the if/elif statements

jasonlyik commented 3 weeks ago

Note that snntorch is not jit traceable because the forward function can either return spikes only or spikes and mem. So may be trouble to add torch QuantizedLinear.

SNNTorch recommends Brevitas library for weight quantization, can look into that instead of QuantizedLinear https://github.com/jeshraghian/snntorch/blob/398c7c45498716d7a60f54e0ac92258a5fd99d41/snntorch/functional/quant.py#L47