 Johannes Gäßler
|
17366df842
Multi GPU support, CUDA refactor, CUDA scratch buffer (#1703)
|
2 anos atrás |
 Georgi Gerganov
|
ecb217db4f
llama : Metal inference (#1642)
|
2 anos atrás |
 Kerfuffle
|
1b78ed2081
Only show -ngl option when relevant + other doc/arg handling updates (#1625)
|
2 anos atrás |
 Vladimir Zorin
|
337aea1139
examples : add --alias option to gpt_params to set use friendly model name (#1614)
|
2 anos atrás |
 DannyDaemonic
|
d2c59b8ba4
Fix for mingw (#1462)
|
2 anos atrás |
 Jason McCartney
|
7694b52b9a
main : make reverse prompt option act as a stop token in non-interactive mode (#1032)
|
2 anos atrás |
|
Georgi Gerganov
|
4b7e245adf
minor : fix compile warnings
|
2 anos atrás |
 Stephan Walter
|
dc271c52ed
Remove unused n_parts parameter (#1509)
|
2 anos atrás |
 zrm
|
63d20469b8
fix get_num_physical_cores() (#1436)
|
2 anos atrás |
|
Johannes Gäßler
|
905d87b70a
ggml : GPU-accelerated token generation (#1412)
|
2 anos atrás |
|
Johannes Gäßler
|
773ee249fb
CLI args use - instead of _, backwards compatible (#1416)
|
2 anos atrás |
 Evan Jones
|
cf348a60e0
main : add option to save full output to session (#1338)
|
2 anos atrás |
|
DannyDaemonic
|
e6a46b0ed1
Locale fix for Windows (#1379)
|
2 anos atrás |
|
DannyDaemonic
|
41654efea8
Interface improvements and `--multiline-input` (previously `--author-mode`) (#1040)
|
2 anos atrás |
|
Georgi Gerganov
|
f9a6364912
llama : require first token to be BOS (#1303)
|
2 anos atrás |
|
Johannes Gäßler
|
1f48b0abcf
Documented CUDA reproducibility, added warning (#1346)
|
2 anos atrás |
 44670
|
2edbdb0f99
main : add --in-suffix option (#1318)
|
2 anos atrás |
|
DannyDaemonic
|
db1080876a
Only escape prompts when used with `-e` (#1311)
|
2 anos atrás |
|
DannyDaemonic
|
2485d7a4d3
Process escape sequences given in prompts (#1173)
|
2 anos atrás |
 slaren
|
bf4b22ffe4
fix missing parameters in `llama_init_from_gpt_params` (#1293)
|
2 anos atrás |
 Ron Evans
|
67c77799e0
examples : add llama_init_from_gpt_params() common function (#1290)
|
2 anos atrás |
 Robert Brisita
|
2bb992f034
llama : allow 0 as a seed number. (#1275)
|
2 anos atrás |
 jon-chuang
|
a5d30b1f53
common : better default number of threads (#934)
|
2 anos atrás |
 Ivan Stepanov
|
dd7eff57d8
llama : new sampling algorithms (#1126)
|
2 anos atrás |
|
Evan Jones
|
1481a9cf25
llama : add session file format and saved sessions in main (#1169)
|
2 anos atrás |
 mgroeber9110
|
9b0a4d4214
examples/main README improvements and some light refactoring (#1131)
|
2 anos atrás |
 slaren
|
315a95a4d3
Add LoRA support (#820)
|
2 anos atrás |
 Pavol Rusnak
|
c85e03d12e
Revert "main : alternative instruct mode (Vicuna support, etc.) (#863)" (#982)
|
2 anos atrás |
 Tomáš Pazdiora
|
f4d277ae17
main : alternative instruct mode (Vicuna support, etc.) (#863)
|
2 anos atrás |
 CRD716
|
0e07e6a839
common : remove unnecessary includes (#947)
|
2 anos atrás |
