From 269e726015184977f363c838f9082f0edaf640f9 Mon Sep 17 00:00:00 2001 From: Lin Xuhao Date: Fri, 18 Sep 2026 17:41:24 +0200 Subject: [PATCH] fix: honor flash attention flag in LLM text encoder attention (#1987) --- src/model/te/llm.hpp | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/src/model/te/llm.hpp b/src/model/te/llm.hpp index 03deb610..b289328e 100644 --- a/src/model/te/llm.hpp +++ b/src/model/te/llm.hpp @@ -1377,7 +1377,7 @@ namespace LLM { x = ggml_ext_cont(ctx->ggml_ctx, kqv); x = ggml_reshape_3d(ctx->ggml_ctx, x, head_dim * num_heads, n_token, N); } else { - x = ggml_ext_attention_ext(ctx, q, k, v, num_heads, attention_mask, true, false); // [N, n_token, hidden_size] + x = ggml_ext_attention_ext(ctx, q, k, v, num_heads, attention_mask, true, ctx->flash_attn_enabled); // [N, n_token, hidden_size] } x = out_proj->forward(ctx, x); // [N, n_token, hidden_size]