* common : refactor common_sampler + grammar logic changes * tests : increase max_tokens to get needed response * batched : fix uninitialized samplers |
||
|---|---|---|
| .. | ||
| CMakeLists.txt | ||
| README.md | ||
| speculative.cpp | ||
README.md
llama.cpp/examples/speculative
Demonstration of speculative decoding and tree-based speculative decoding techniques
More info: