llm: Enable flash attention for mistral3 by default

This commit is contained in:
Jesse Gross 2025-12-04 12:16:52 -08:00 committed by Jesse Gross
parent 1108d8b34e
commit 9191dfaf05
1 changed files with 1 additions and 0 deletions

View File

@ -831,6 +831,7 @@ func (f GGML) FlashAttention() bool {
return slices.Contains([]string{
"gemma3",
"gptoss", "gpt-oss",
"mistral3",
"qwen3", "qwen3moe",
"qwen3vl", "qwen3vlmoe",
}, f.KV().String("general.architecture"))