Georgi Gerganov ec893798b7 llama : custom attention mask + parallel decoding + no context swaps (#3228) 2 лет назад
..
CMakeLists.txt 47068e5170 speculative : PoC for speeding-up inference via speculative sampling (#2926) 2 лет назад
speculative.cpp ec893798b7 llama : custom attention mask + parallel decoding + no context swaps (#3228) 2 лет назад