| .. |
|
CMakeLists.txt
|
938943cdbf
llama : move vocab, grammar and sampling into separate files (#8508)
|
1 год назад |
|
llama-grammar.cpp
|
df270ef745
llama : refactor sampling v2 (#9294)
|
1 год назад |
|
llama-grammar.h
|
df270ef745
llama : refactor sampling v2 (#9294)
|
1 год назад |
|
llama-impl.h
|
cea1486ecf
log : add CONT level for continuing previous log entry (#9610)
|
1 год назад |
|
llama-sampling.cpp
|
b0f27361f3
sampling : avoid expensive softmax during greedy sampling (#9605)
|
1 год назад |
|
llama-sampling.h
|
19f4a7b296
llama : refactor samplers internal implementation (#9370)
|
1 год назад |
|
llama-vocab.cpp
|
11ac9800af
llama : improve infill support and special token detection (#9798)
|
1 год назад |
|
llama-vocab.h
|
11ac9800af
llama : improve infill support and special token detection (#9798)
|
1 год назад |
|
llama.cpp
|
11ac9800af
llama : improve infill support and special token detection (#9798)
|
1 год назад |
|
unicode-data.cpp
|
458367a906
server : better security control for public deployments (#9776)
|
1 год назад |
|
unicode-data.h
|
a39ab216aa
llama : reduce compile time and binary size (#9712)
|
1 год назад |
|
unicode.cpp
|
a39ab216aa
llama : reduce compile time and binary size (#9712)
|
1 год назад |
|
unicode.h
|
938943cdbf
llama : move vocab, grammar and sampling into separate files (#8508)
|
1 год назад |
Georgi Gerganov
11ac9800af
llama : improve infill support and special token detection (#9798)