From c8e0878814b4d19200d65571d3d2d35b4b48fd3e Mon Sep 17 00:00:00 2001 From: Daniel Hiltgen Date: Fri, 3 Apr 2026 12:46:18 -0700 Subject: [PATCH] enable flash attention for gemma4 (#15296) --- fs/ggml/ggml.go | 1 + 1 file changed, 1 insertion(+) diff --git a/fs/ggml/ggml.go b/fs/ggml/ggml.go index 9788297cc..e23d345cd 100644 --- a/fs/ggml/ggml.go +++ b/fs/ggml/ggml.go @@ -890,6 +890,7 @@ func (f GGML) FlashAttention() bool { return slices.Contains([]string{ "bert", "gemma3", + "gemma4", "glm4moelite", "glmocr", "gptoss", "gpt-oss",