 Georgi Gerganov
|
a9cae48003
tests : add non-cont unary tests (#7857)
|
1 سال پیش |
|
Georgi Gerganov
|
2b3389677a
ggml : refactor rope norm/neox (#7634)
|
1 سال پیش |
 woachk
|
9e405b6e2e
kompute : implement op_getrows_f32 (#6403)
|
1 سال پیش |
|
Georgi Gerganov
|
55d62262a9
metal : remove invalid asserts (#7617)
|
1 سال پیش |
|
Georgi Gerganov
|
975ec63ff2
metal : add missing asserts (#7617)
|
1 سال پیش |
|
Georgi Gerganov
|
fb76ec31a9
ggml : fix YARN + add tests + add asserts (#7617)
|
1 سال پیش |
 liuwei-git
|
201cc11afa
llama : add phi3 128K model support (#7225)
|
1 سال پیش |
|
Georgi Gerganov
|
9cb317f77e
ggml : full ALiBi support (#7192)
|
1 سال پیش |
|
Georgi Gerganov
|
9c67c2773d
ggml : add Flash Attention (#5021)
|
1 سال پیش |
 compilade
|
557410b8f0
llama : greatly reduce output buffer memory usage (#6122)
|
1 سال پیش |
 slaren
|
2bf8d0f7c4
backend : offload large batches to GPU (#6083)
|
1 سال پیش |
|
slaren
|
f30ea47a87
llama : add pipeline parallelism support (#6017)
|
1 سال پیش |
 Michael Podvitskiy
|
9fa2627347
ggml : introduce ggml_status (ggml/750)
|
1 سال پیش |
 UEXTM.com
|
5f70671856
Introduce backend GUIDs (ggml/743)
|
1 سال پیش |
 Jared Van Bortel
|
fbf1ddec69
Nomic Vulkan backend (#4456)
|
1 سال پیش |
