Georgi Gerganov f66f582927 llama : refactor `src/llama.cpp` (#10902) vor 1 Jahr
..
CMakeLists.txt 7cc2d2c889 ggml : move AMX to the CPU backend (#10570) vor 1 Jahr
README.md 6d341ab6c5 speculative : implement stochastic speculative sampling (#5625) vor 1 Jahr
speculative.cpp f66f582927 llama : refactor `src/llama.cpp` (#10902) vor 1 Jahr

README.md

llama.cpp/examples/speculative

Demonstration of speculative decoding and tree-based speculative decoding techniques

More info: