SparseDecoding: Decoding-Aware Pruning for Accurate and Efficient LLM Inference
SparseDecoding prunes LLMs using decoding activations, speeding generation up to 1.48x.
2 stories, newest first · one card per story
SparseDecoding prunes LLMs using decoding activations, speeding generation up to 1.48x.

The US arrested Earthmade CEO Greg Lui for allegedly smuggling over $300 million in Nvidia AI chips to China.
Today 2.5K readers · 2.8K views · 144 reads · all time 206K views