This website works better with JavaScript
Начало
Каталог
Помощ
Вход
cturan
/
llama.cpp
огледало от
https://github.com/cturan/llama.cpp
Наблюдаван
1
Харесван
0
Разклонения
0
Файлове
Задачи
0
Уики
Клон:
master
Клонове
Маркери
k2v2
master
minimax
qwen3_next
qwen3_next_optimized
toolinjection
test
b6814
llama.cpp
/
examples
/
speculative
Georgi Gerganov
4301e27319
common : restore grammar-based rejection sampling (
#18137
)
преди 1 месец
..
CMakeLists.txt
7cc2d2c889
ggml : move AMX to the CPU backend (
#10570
)
преди 1 година
README.md
68ff663a04
repo : update links to new url (
#11886
)
преди 11 месеца
speculative.cpp
4301e27319
common : restore grammar-based rejection sampling (
#18137
)
преди 1 месец
README.md
llama.cpp/examples/speculative
Demonstration of speculative decoding and tree-based speculative decoding techniques
More info:
https://github.com/ggml-org/llama.cpp/pull/2926
https://github.com/ggml-org/llama.cpp/pull/3624
https://github.com/ggml-org/llama.cpp/pull/5625