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

Single load for half2

Browse source
This commit is contained in:
Aidan 2024-07-02 10:09:20 +01:00
parent 730819cf65
commit 80d3b39bff
1 changed files with 3 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

5
ggml/src/ggml-sycl/dequantize.hpp
View file

@ -319,8 +319,9 @@ static void dequantize_block_q4_K(const void * __restrict__ vx, dst_t * __restri
dst_t * y = yy + i*QK_K + 64*il + n*ir;
const float dall = x[i].dm[0];
const float dmin = x[i].dm[1];
const sycl::half2 dm = x[i].dm;
const float dall = dm[0];
const float dmin = dm[1];
const uint8_t * q = x[i].qs + 32*il + n*ir;