From aed0afb40884d0066ea64046fdd0d70575accdf2 Mon Sep 17 00:00:00 2001 From: Molly Sophia Date: Tue, 7 Jan 2025 17:00:40 +0800 Subject: [PATCH] Update ggml/src/ggml-cuda/gla.cu Co-authored-by: Georgi Gerganov --- ggml/src/ggml-cuda/gla.cu | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/ggml/src/ggml-cuda/gla.cu b/ggml/src/ggml-cuda/gla.cu index 3debbf933..f7d615a82 100644 --- a/ggml/src/ggml-cuda/gla.cu +++ b/ggml/src/ggml-cuda/gla.cu @@ -31,10 +31,10 @@ static __global__ void gated_linear_attn_f32(const int B, const int T, const int const float _v = v[t]; float y = 0; for (int j = 0; j < head_size; j += 4) { - const float4& k = (float4&)(_k[j]); - const float4& r = (float4&)(_r[j]); - const float4& td = (float4&)(_td[j]); - float4& s = (float4&)(state[j]); + const float4 & k = (float4 &)(_k[j]); + const float4 & r = (float4 &)(_r[j]); + const float4 & td = (float4 &)(_td[j]); + float4 & s = (float4 &)(state[j]); float4 kv; kv.x = k.x * _v;