mirror of
https://github.com/likelovewant/ollama-for-amd.git
synced 2025-12-21 14:26:30 +00:00
bd6c1d6b49
* flash attn: add auto mode for llama engine If the user does not specify fa in the environment, use auto-mode. * review comments * ensure kv cache quantized types have FA explicitly enabled additional review comments
23 KiB
23 KiB