cturan/llama.cpp

mirror da https://github.com/cturan/llama.cpp

Autore	SHA1 Messaggio	Data
compilade	557410b8f0 llama : greatly reduce output buffer memory usage (#6122)	1 anno fa
slaren	2bf8d0f7c4 backend : offload large batches to GPU (#6083)	1 anno fa
slaren	f30ea47a87 llama : add pipeline parallelism support (#6017)	1 anno fa
Michael Podvitskiy	9fa2627347 ggml : introduce ggml_status (ggml/750)	1 anno fa
UEXTM.com	5f70671856 Introduce backend GUIDs (ggml/743)	1 anno fa
Jared Van Bortel	fbf1ddec69 Nomic Vulkan backend (#4456)	2 anni fa