Skip to content

Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.

llm: Enable flash attention by default for qwen3 and qwen3moe

Jesse Gross0bda72892cc8
diff --git a/fs/ggml/ggml.go b/fs/ggml/ggml.go
index 58803f58f..d34a69138 100644
--- a/fs/ggml/ggml.go
+++ b/fs/ggml/ggml.go
@@ -899,6 +899,8 @@ func (f GGML) SupportsFlashAttention() bool {
func (f GGML) FlashAttention() bool {
return slices.Contains([]string{
"gptoss", "gpt-oss",
+ "qwen3",
+ "qwen3moe",
}, f.KV().String("general.architecture"))
}