This website works better with JavaScript
Почетна
Преглед
Помоћ
Пријавите се
cturan
/
llama.cpp
огледало од
https://github.com/cturan/llama.cpp
Прати
1
Волим
0
Креирај огранак
0
Датотеке
Дискусије
0
Вики
Дрво:
b231b37b09
Гране
Ознаке
k2v2
master
minimax
qwen3_next
qwen3_next_optimized
toolinjection
test
b6814
llama.cpp
/
examples
/
speculative
Jared Van Bortel
1b67731e18
BERT tokenizer fixes (
#6498
)
пре 1 година
..
CMakeLists.txt
b12fa0d1c1
build : link against build info instead of compiling against it (
#3879
)
пре 2 година
README.md
6d341ab6c5
speculative : implement stochastic speculative sampling (
#5625
)
пре 1 година
speculative.cpp
1b67731e18
BERT tokenizer fixes (
#6498
)
пре 1 година
README.md
llama.cpp/examples/speculative
Demonstration of speculative decoding and tree-based speculative decoding techniques
More info:
https://github.com/ggerganov/llama.cpp/pull/2926
https://github.com/ggerganov/llama.cpp/pull/3624
https://github.com/ggerganov/llama.cpp/pull/5625