mirror of
https://github.com/likelovewant/ollama-for-amd.git
synced 2025-12-22 06:43:57 +00:00
90ca84172c
* Fix embeddings memory corruption The patch was leading to a buffer overrun corruption. Once removed though, parallism in server.cpp lead to hitting an assert due to slot/seq IDs being >= token count. To work around this, only use slot 0 for embeddings. * Fix embed integration test assumption The token eval count has changed with recent llama.cpp bumps (0.3.5+)
28 KiB
28 KiB