llm: Enable flash attention for mistral3 by default

9191dfaf · Jesse Gross · Jesse Gross · 1108d8b3 · 9191dfaf
Commit 9191dfaf authored Dec 04, 2025 by Jesse Gross Committed by Jesse Gross Dec 04, 2025
Show whitespace changes
Inline Side-by-side

Showing with 1 addition and 0 deletions

fs/ggml/ggml.go fs/ggml/ggml.go +1 -0

No files found.
--- a/fs/ggml/ggml.go
+++ b/fs/ggml/ggml.go
@@ -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"))