diff options
| author | Mitja Felicijan <mitja.felicijan@gmail.com> | 2026-02-12 20:57:17 +0100 |
|---|---|---|
| committer | Mitja Felicijan <mitja.felicijan@gmail.com> | 2026-02-12 20:57:17 +0100 |
| commit | b333b06772c89d96aacb5490d6a219fba7c09cc6 (patch) | |
| tree | 211df60083a5946baa2ed61d33d8121b7e251b06 /llama.cpp/examples/lookahead/README.md | |
| download | llmnpc-b333b06772c89d96aacb5490d6a219fba7c09cc6.tar.gz | |
Engage!
Diffstat (limited to 'llama.cpp/examples/lookahead/README.md')
| -rw-r--r-- | llama.cpp/examples/lookahead/README.md | 13 |
1 files changed, 13 insertions, 0 deletions
diff --git a/llama.cpp/examples/lookahead/README.md b/llama.cpp/examples/lookahead/README.md new file mode 100644 index 0000000..c82de2a --- /dev/null +++ b/llama.cpp/examples/lookahead/README.md @@ -0,0 +1,13 @@ +# 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: + +```bash +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 +``` |