Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
qwen3vl: enable flash attention by default (#12862)
Michael Yang75e75d9afea9
diff --git a/fs/ggml/ggml.go b/fs/ggml/ggml.goindex c0ca068ab..909104c64 100644--- a/fs/ggml/ggml.go+++ b/fs/ggml/ggml.go@@ -895,8 +895,8 @@ func (f GGML) FlashAttention() bool {return slices.Contains([]string{"gemma3","gptoss", "gpt-oss",- "qwen3",- "qwen3moe",+ "qwen3", "qwen3moe",+ "qwen3vl", "qwen3vlmoe",}, f.KV().String("general.architecture"))}