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

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
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
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