context : allow cache-less context for embeddings #13108
ggerganov
merged
7 commits into
master
from
gg/embeddings-no-kv
Base automatically changed from
gg/llama-kv-cache-v6
to
master
1 year ago
Green-Sky
commented
on 2025-05-02
context : allow cache-less context for embeddings
9770efa3
context : enable reranking with encode()
a21ff6c2
context : encode() clears embd_seq
c14ee723
examples : use llama_encode() when appropriate
c7092756
models : nomic bert moe does not require KV cache
97b975d4
llama : update comments for llama_decode/llama_encode
3b4f6c0e
context : update warning log [no ci]
abe25e7d
aviallon
commented
on 2025-05-09
Login to write a write a comment.
Login via GitHub