tqcq/llama.cpp
0
0
Fork 0
mirror of https://github.com/ggml-org/llama.cpp.git synced 2025-06-26 19:55:04 +00:00
Code Issues Packages Projects Releases Wiki Activity

CUDA: Fix models with output size != 32000 (#2480)

Browse Source
This commit is contained in:
Johannes Gäßler
2023-08-02 16:48:10 +02:00
committed by GitHub
parent 220d931864
commit 4f6b60c776
2 changed files with 249 additions and 75 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
CMakeLists.txt
View File

@ -280,8 +280,8 @@ if (LLAMA_CUBLAS)
# 52 == lowest CUDA 12 standard
# 60 == f16 CUDA intrinsics
# 61 == integer CUDA intrinsics
# 70 == (assumed) compute capability at which unrolling a loop in mul_mat_q kernels is faster
if (LLAMA_CUDA_DMMV_F16)
# 70 == compute capability at which unrolling a loop in mul_mat_q kernels is faster
if (LLAMA_CUDA_F16 OR LLAMA_CUDA_DMMV_F16)
set(CMAKE_CUDA_ARCHITECTURES "60;61;70") # needed for f16 CUDA intrinsics
else()
set(CMAKE_CUDA_ARCHITECTURES "52;61;70") # lowest CUDA 12 standard + lowest for integer intrinsics