mirror of
https://github.com/ggerganov/llama.cpp.git
synced 2025-04-17 20:16:09 +00:00

* (wip) refactor downloading system [no ci] * fix all examples * fix mmproj with -hf * gemma3: update readme * only handle mmproj in llava example * fix multi-shard download * windows: fix problem with std::min and std::max * fix 2
llama.cpp/examples/speculative
Demonstration of speculative decoding and tree-based speculative decoding techniques
More info: