vbatts/llama.cpp
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Update ggml/src/ggml-cuda/gla.cu

Browse source 
Co-authored-by: Georgi Gerganov <ggerganov@gmail.com>
This commit is contained in:
Molly Sophia 2025-01-07 17:00:40 +08:00 • committed by GitHub
parent 331581b2e3
commit aed0afb408
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 4 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

8
ggml/src/ggml-cuda/gla.cu
View file

@ -31,10 +31,10 @@ static __global__ void gated_linear_attn_f32(const int B, const int T, const int
const float _v = v[t]; const float _v = v[t];
float y = 0; float y = 0;
for (int j = 0; j < head_size; j += 4) { for (int j = 0; j < head_size; j += 4) {
const float4& k = (float4&)(_k[j]); const float4 & k = (float4 &)(_k[j]);
const float4& r = (float4&)(_r[j]); const float4 & r = (float4 &)(_r[j]);
const float4& td = (float4&)(_td[j]); const float4 & td = (float4 &)(_td[j]);
float4& s = (float4&)(state[j]); float4 & s = (float4 &)(state[j]);
float4 kv; float4 kv;
kv.x = k.x * _v; kv.x = k.x * _v;