KanakMalpani/Binary-Neural-Networks

Open Issues Need Help

test: assert every CLI subcommand appears in --help epilog or README quick start about 3 hours ago

enhancement good first issue

Extreme low-bit inference lab: pack weights to 1–1.58 bits and run real XNOR/popcount kernels on CPU/edge — honest STE training, not fake GPU 32× from sign().

Python

#binary-neural-networks#cpu-inference#edge-ai#machine-learning#model-compression#pytorch#quantization#ternary#xnor

docs: add a one-screen 'When NOT to use BNN' callout to README about 3 hours ago

documentation good first issue

KanakMalpani/Binary-Neural-Networks

Extreme low-bit inference lab: pack weights to 1–1.58 bits and run real XNOR/popcount kernels on CPU/edge — honest STE training, not fake GPU 32× from sign().

Python

#binary-neural-networks#cpu-inference#edge-ai#machine-learning#model-compression#pytorch#quantization#ternary#xnor