Mirrors/llama.cpp
1
0
Fork 0
mirror of https://github.com/ggerganov/llama.cpp.git synced 2025-01-23 09:59:18 +01:00
Code Issues Packages Projects Releases Wiki Activity

cuda : fix LLAMA_CUDA_F16 build (#6298)

Browse Source
This commit is contained in:
slaren 2024-03-25 15:43:22 +01:00 committed by GitHub
parent ae1f211ce2
commit 2f34b865b6
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
1 changed files with 1 additions and 0 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
ggml-cuda/dmmv.cu
View File

@ -1,5 +1,6 @@
#include "dmmv.cuh" #include "dmmv.cuh"
#include "dequantize.cuh" #include "dequantize.cuh"
#include "convert.cuh"
// dmmv = dequantize_mul_mat_vec // dmmv = dequantize_mul_mat_vec
#ifndef GGML_CUDA_DMMV_X #ifndef GGML_CUDA_DMMV_X