 Georgi Gerganov
|
9c67c2773d
ggml : add Flash Attention (#5021)
|
1 жил өмнө |
 compilade
|
557410b8f0
llama : greatly reduce output buffer memory usage (#6122)
|
1 жил өмнө |
 slaren
|
2bf8d0f7c4
backend : offload large batches to GPU (#6083)
|
1 жил өмнө |
|
slaren
|
f30ea47a87
llama : add pipeline parallelism support (#6017)
|
1 жил өмнө |
 Michael Podvitskiy
|
9fa2627347
ggml : introduce ggml_status (ggml/750)
|
1 жил өмнө |
 UEXTM.com
|
5f70671856
Introduce backend GUIDs (ggml/743)
|
1 жил өмнө |
 Jared Van Bortel
|
fbf1ddec69
Nomic Vulkan backend (#4456)
|
1 жил өмнө |
