COMMITS
November 1, 2023
A
Bump version
Andrei Betlen committed
N
Add missing n_seq_id to llama_batch (#842)
NickAlgra committed
S
Fix for shared library not found and compile issues in Windows (#848)
Sujeendran Menon committed
C
llama: fix exception in Llama.__del__ (#846)
cebtenzzre committed
D
Iterate over tokens that should be biased rather than the entire vocabulary. (#851)
David Ponce committed
M
D
Pass-Through grammar parameter in web server. (#855) Closes #778
Daniel Thuerck committed
A
Update llama_types.py (#849)
Adam Katora committed
A
Update llama.cpp
Andrei Betlen committed
A
Update llama.cpp
Andrei Betlen committed
October 24, 2023
A
Update llama.cpp
Andrei Betlen committed
October 20, 2023
A
Update llama.cpp
Andrei Betlen committed
October 19, 2023
A
Update llama.cpp
Andrei Betlen committed
A
Enable finish reason tests
Andrei Betlen committed
G
Fix streaming doesn't return finish reason (#798)
gmcgoldr committed
A
Merge branch 'main' of github.com:abetlen/llama_cpp_python into main
Andrei Betlen committed
A
Re-enable tests completion function
Andrei Betlen committed
A
Update llama.cpp
Andrei Betlen committed
October 18, 2023
X
update value check for n_gpu_layers field (#826)
Xiaoyu Kevin Hu committed
October 15, 2023
A
Update llama.cpp
Andrei Betlen committed
P
Make use of suppress_stdout_stderr when freeing model (#803)
Pierre Alexandre SCHEMBRI committed
M
Fix repeat greeting (#808)
Ma, Guokai committed
E
Add validation for tensor_split size exceeding LLAMA_MAX_DEVICES (#820)
Eric Liu committed
October 12, 2023
A
Update llama.cpp
Andrei Betlen committed
October 10, 2023
A
Update llama.cpp
Andrei Betlen committed
A
Print traceback on server error
Andrei Betlen committed
October 5, 2023
A
Update llama.cpp
Andrei Betlen committed
A
Update llama.cpp
Andrei Betlen committed
October 3, 2023
A
Merge branch 'main' of github.com:abetlen/llama_cpp_python into main
Andrei Betlen committed
A
Update llama.cpp
Andrei Betlen committed