Implementation of PLDR-LLM with KV-cache and G-cache in Pytorch for the paper titled "PLDR-LLMs Learn A Generalizable Tensor Operator That Can Replace Its Own Deep Neural Net At Inference"
nlp machine-learning natural-language-processing deep-learning pytorch transformer dag directed-acyclic-graph kv-cache large-language-models llm power-law-graph-attention pldr-llm power-law-decoder-representations g-cache kvg-cache
-
Updated
Mar 19, 2025 - Python