diff --git a/fs/ggml/ggml.go b/fs/ggml/ggml.go index 920eff74a2..fcb3d9fdb4 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 attention func (f GGML) FlashAttention() bool { return slices.Contains([]string{ + "gemma3", "gptoss", "gpt-oss", "qwen3", "qwen3moe",