Get up and running with Kimi, GLM, MiniMax, DeepSeek, gpt-oss, Qwen, Gemma and other models.
llm: Enable flash attention by default for gemma3
Jesse Grossc3c85aa06c1b
diff --git a/fs/ggml/ggml.go b/fs/ggml/ggml.goindex 920eff74a..fcb3d9fdb 100644--- a/fs/ggml/ggml.go+++ b/fs/ggml/ggml.go@@ -893,6 +893,7 @@ func (f GGML) SupportsFlashAttention() bool {// FlashAttention checks if the model should enable flash attentionfunc (f GGML) FlashAttention() bool {return slices.Contains([]string{+ "gemma3","gptoss", "gpt-oss","qwen3","qwen3moe",