char-fork/llama.cpp
git clone https://git.t4t.associates/char-fork/llama.cpp
2f3701407
char/aliceai-t5-moe
llama.cpp/examples/lookahead
Demonstration of lookahead decoding technique:
https://lmsys.org/blog/2023-11-21-lookahead-decoding/
More info: https://github.com/ggml-org/llama.cpp/pull/4207
Sample command:
llama-lookahead -hf ggml-org/Qwen2.5-Coder-3B-Q8_0-GGUF-p "// network server implemented in C\n// author: Peter Hacker\n\n#include" -e -ngl 99-t 4-n 512-c 4096-kvu
1# llama.cpp/examples/lookahead 2 3Demonstration of lookahead decoding technique: 4 5https://lmsys.org/blog/2023-11-21-lookahead-decoding/ 6 7More info: https://github.com/ggml-org/llama.cpp/pull/4207 8 9Sample command: 10 11``` bash 12llama-lookahead -hf ggml-org/Qwen2.5-Coder-3B-Q8_0-GGUF -p "// network server implemented in C\n// author: Peter Hacker\n\n#include" -e -ngl 99 -t 4 -n 512 -c 4096 -kvu 13```