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

cuda : fix convert function (#1412)

Browse source
This commit is contained in:
Georgi Gerganov 2023-05-13 17:40:58 +03:00
parent bda4d7c215
commit 08737ef720
1 changed files with 1 additions and 1 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

2
ggml-cuda.cu
View file

@ -414,7 +414,7 @@ static dequantize_mul_mat_vec_cuda_t ggml_get_dequantize_mul_mat_vec_cuda(ggml_t
case GGML_TYPE_Q8_0: case GGML_TYPE_Q8_0:
return dequantize_mul_mat_vec_q8_0_cuda; return dequantize_mul_mat_vec_q8_0_cuda;
case GGML_TYPE_F16: case GGML_TYPE_F16:
return dequantize_mul_mat_vec_q8_0_cuda; return convert_mul_mat_vec_f16_cuda;
default: default:
return nullptr; return nullptr;
} }