transformers
a065282c - Fix Ministral3 and Mistral4 ignoring packed sequences under FlashAttention (#50450)

Commit
5 days ago
Fix Ministral3 and Mistral4 ignoring packed sequences under FlashAttention (#50450) Ministral3Attention and Mistral4Attention take position_ids as a named argument (for the Llama 4 query scaling) and no longer forwarded it to the attention function, so FlashAttention could not detect padding-free packed rows and let documents attend across boundaries. Forward position_ids to attention_interface, as the other Mistral-family models do.
Author
Parents
Loading