This website works better with JavaScript
Acasă
Explorează
Ajutor
Autentificare
cturan
/
llama.cpp
oglindă de
https://github.com/cturan/llama.cpp
Urmărește
1
Stea
0
Bifurcare
0
Fisiere
Probleme
0
Wiki
Arbore:
963552903f
Ramuri
Etichete
k2v2
master
minimax
qwen3_next
qwen3_next_optimized
toolinjection
test
b6814
llama.cpp
/
examples
/
speculative
Georgi Gerganov
1442677f92
common : refactor cli arg parsing (
#7675
)
1 an în urmă
..
CMakeLists.txt
b12fa0d1c1
build : link against build info instead of compiling against it (
#3879
)
2 ani în urmă
README.md
6d341ab6c5
speculative : implement stochastic speculative sampling (
#5625
)
1 an în urmă
speculative.cpp
1442677f92
common : refactor cli arg parsing (
#7675
)
1 an în urmă
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