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

iq3_s_mult: also CUDA

Browse source
This commit is contained in:
Iwan Kawrakow 2024-03-03 19:12:05 +02:00
parent e5e72562c5
commit f2c2bd6b26
2 changed files with 18 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

2
ggml-quants.c
View file

@ -10037,6 +10037,8 @@ void ggml_vec_dot_iq3_s_q8_K (int n, float * GGML_RESTRICT s, size_t bs, const v
UNUSED(by);
UNUSED(bs);
GGML_ASSERT(IQ3S_BLOCK_SIZE == 32 && "IQ3S_BLOCK_SIZE != 32 is not implemented");
const block_iq3_s * restrict x = vx;
const block_q8_K * restrict y = vy;