llama-cpp-python icon indicating copy to clipboard operation
llama-cpp-python copied to clipboard
verified publisher icon abetlen

Fix multi-sequence embeddings

Open iamlemec opened this issue 5 months ago • 1 comments

Fixes multi-sequence (batch) embeddings by handling n_seq_max and kv_unified flags. See discussion in #2051.

iamlemec avatar Aug 19 '25 19:08 iamlemec

@abetlen any updates yet?

LimePencil avatar Sep 15 '25 14:09 LimePencil