This website requires JavaScript.
Explore
Help
Sign in
vbatts
/
llama.cpp
Watch
1
Star
0
Fork
You've already forked llama.cpp
0
Code
Issues
Pull requests
Projects
Releases
Packages
Wiki
Activity
Actions
2338
commits
380
branches
3056
tags
365
MiB
gg/fix-embeddings-wip
Commit graph
3 commits
Author
SHA1
Message
Date
Georgi Gerganov
4ec0e9abbf
wip
2024-03-04 17:07:12 +02:00
Georgi Gerganov
eb42596277
llama : do not use KV cache for non-causal models
...
ggml-ci
2024-03-04 13:34:16 +02:00
Georgi Gerganov
d0347840c1
llama : fix embeddings
...
ggml-ci
2024-03-04 11:43:16 +02:00