 Georgi Gerganov
|
745aa5319b
llama : deprecate llama_kv_self_ API (#14030)
|
hai 7 meses |
|
Georgi Gerganov
|
e0dbec0bc6
llama : refactor llama_context, llama_kv_cache, llm_build_context (#12181)
|
hai 10 meses |
 Jhen-Jie Hong
|
f117d84b48
swift : fix llama-vocab api usage (#11645)
|
hai 11 meses |
|
Georgi Gerganov
|
afa8a9ec9b
llama : add `llama_vocab`, functions -> methods, naming (#11110)
|
hai 1 ano |
|
Georgi Gerganov
|
0abc6a2c25
llama : llama_perf + option to disable timings during decode (#9355)
|
hai 1 ano |
 slaren
|
5fb5e24811
llama : minor sampling refactor (2) (#9386)
|
hai 1 ano |
|
Georgi Gerganov
|
df270ef745
llama : refactor sampling v2 (#9294)
|
hai 1 ano |
 jaime-m-p
|
213701b51a
Detokenizer fixes (#8039)
|
hai 1 ano |
|
Georgi Gerganov
|
40f74e4d73
llama : add option to render special/control tokens (#6807)
|
hai 1 ano |
 Pedro Cuenca
|
b97bc3966e
llama : support Llama 3 HF conversion (#6745)
|
hai 1 ano |
 bmwl
|
f486f6e1e5
ggml : add numa options (#5377)
|
hai 1 ano |
 Miwa / Ensan
|
5c9f90cba1
swift : fix prompt tokenization logic (#4321)
|
%!s(int64=2) %!d(string=hai) anos |
|
Miwa / Ensan
|
b220222a64
swift : fix token_to_piece implementation (#4278)
|
%!s(int64=2) %!d(string=hai) anos |
 eastriver
|
2568a4bf54
main.swift : fix eos checking (#4197)
|
%!s(int64=2) %!d(string=hai) anos |
|
Georgi Gerganov
|
0e89203b51
speculative : add tree-based sampling example (#3624)
|
%!s(int64=2) %!d(string=hai) anos |
 staviq
|
1a159553f9
tokenizer : special token handling (#3538)
|
%!s(int64=2) %!d(string=hai) anos |
 Zane Shannon
|
24ba3d829e
examples : add batched.swift + improve CI for swift (#3562)
|
%!s(int64=2) %!d(string=hai) anos |
