llama.cpp
00ae55b3 - server : hide ctx_sampling->prev behind API (#3696)

Commit

2 years ago

server : hide ctx_sampling->prev behind API (#3696)

References

#3677 - server : parallel decoding and multimodal (cont)

Author

ggerganov

ggerganov

Committer

ggerganov

ggerganov

Parents

Loading