llama.cpp-rocm/include at 99bd4ac28c32cd17c0e337ff5601393b033dc5fc - llama.cpp-rocm - Gitea: Git with a cup of tea

wylab/llama.cpp-rocm

forked from wylab/llama.cpp

Files

T

History

Georgi GerganovandGitHub 99bd4ac28c llama : infill sampling handle very long tokens (#9924 )

* llama : infill sampling handle very long tokens

ggml-ci

* cont : better indices

ggml-ci

2024-10-17 22:32:47 +03:00

..

llama.h

llama : infill sampling handle very long tokens (#9924 )

2024-10-17 22:32:47 +03:00