COMMITS
/ examples/save-load-state/save-load-state.cpp November 25, 2024
G
speculative : refactor and add a simpler example (#10362)
Georgi Gerganov committed
October 21, 2024
G
llama : default sampling changes + greedy update (#9897)
Georgi Gerganov committed
October 18, 2024
X
llama : remove all_pos_0, all_pos_1, all_seq_id from llama_batch (#9745)
Xuan Son Nguyen committed
October 10, 2024
D
common : use common_ prefix for common library functions (#9805)
Diego Devesa committed
September 9, 2024
X
common : move arg parser code to `arg.cpp` (#9388)
Xuan Son Nguyen committed
S
llama : minor sampling refactor (2) (#9386)
slaren committed
September 7, 2024
X
common : refactor arg parser (#9308)
Xuan Son Nguyen committed
G
llama : refactor sampling v2 (#9294)
Georgi Gerganov committed
August 5, 2024
L
common : Changed tuple to struct (TODO fix) (#8823)
Liu Jia committed
July 28, 2024
C
llama : refactor session file management (#8699)
compilade committed
June 4, 2024
G
common : refactor cli arg parsing (#7675)
Georgi Gerganov committed
April 8, 2024
J
llama : save and restore kv cache for single seq id (#6341)
Jan Boon committed
January 13, 2024
D
llama : minimize size used for state save/load (#4820)
David Friehs committed
November 2, 2023
C
build : link against build info instead of compiling against it (#3879)
cebtenzzre committed
October 17, 2023
G
save-load-state : fix example + add ci test (#3655)
Georgi Gerganov committed
October 11, 2023
K
common : fix mirostat state when using multiple sequences (#3543)
Kerfuffle committed
September 28, 2023
S
G
llama : custom attention mask + parallel decoding + no context swaps (#3228)
Georgi Gerganov committed
September 18, 2023
C
make : restore build-info.h dependency for several targets (#3205)
Cebtenzzre committed
September 15, 2023
C
examples : add compiler version and target to build info (#2998)
Cebtenzzre committed
September 7, 2023
C
fix some warnings from gcc and clang-tidy (#3038)
Cebtenzzre committed
August 27, 2023
G
llama : more tokenizer fixes (#2810)
Georgi Gerganov committed
August 21, 2023
G
gguf : new file format with flexible meta data (beta) (#2398)
Georgi Gerganov committed
July 28, 2023
R
llama : use n_embd_gqa instead of n_embd to handle llama-2 70B (#2433)
Rand Xie committed
June 24, 2023
D
llama : make model stateless and context stateful (llama_state) (#1797)
Didzis Gosko committed
June 16, 2023
B
build : fix and ignore MSVC warnings (#1889)
Borislav Stanimirov committed
May 17, 2023
S
Remove unused n_parts parameter (#1509)
Stephan Walter committed
May 16, 2023
A
define default model path once, sync path with readme (#1366)
András Salamon committed
May 1, 2023
D
Add git-based build information for better issue tracking (#1232)
DannyDaemonic committed
April 29, 2023
G
build : fix reference to old llama_util.h
Georgi Gerganov committed
G
examples : fix save-load-state + rename llama-util.h
Georgi Gerganov committed
I
llama : new sampling algorithms (#1126)
Ivan Stepanov committed
April 24, 2023
X
examples : add save_load_state example (#1150)
xaedes committed