llama.cpp
Fixed embeddings when offloading non-repeating layers
#1891

Merged

Fixed embeddings when offloading non-repeating layers #1891

ggerganov merged 1 commit into ggml-org:master from JohannesGaessler:cuda-embeddings-fix

JohannesGaessler changed the title ~~Fixed embeddings when offloading KV cache~~ Fixed embeddings when offloading non-repeating layers 2 years ago

Fixed embd when offloading non-repeating layers

1170a957

JohannesGaessler force pushed to 1170a957 2 years ago

slaren approved these changes on 2023-06-16

ggerganov merged ac3b8869 into master 2 years ago

Reviewers

slaren

Assignees

No one assigned

Labels

None yet

Milestone

No milestone

llama.cpp Fixed embeddings when offloading non-repeating layers #1891 Merged

Fixed embeddings when offloading non-repeating layers #1891

llama.cpp
Fixed embeddings when offloading non-repeating layers
#1891

Merged