ceos/unsloth
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions

Remove extra CUDA cmake flags to align Windows with Linux build

Browse source 
Drop GGML_CUDA_FA_ALL_QUANTS, GGML_CUDA_F16, GGML_CUDA_GRAPHS,
GGML_CUDA_FORCE_CUBLAS, and GGML_CUDA_PEER_MAX_BATCH_SIZE flags.
The Linux build in setup.sh only sets GGML_CUDA=ON and lets llama.cpp
use its defaults for everything else. Keep Windows consistent.
This commit is contained in:
Daniel Han 2026-03-18 06:16:37 +00:00
commit 7125772c0a
1 changed files with 0 additions and 5 deletions
Download patch file Download diff file Expand all files Collapse all files

5
studio/setup.ps1
View file

@ -1146,11 +1146,6 @@ if (Test-Path $LlamaServerBin) {
$CmakeArgs += "-DCUDAToolkit_ROOT=$CudaToolkitRoot"
$CmakeArgs += "-DCUDA_TOOLKIT_ROOT_DIR=$CudaToolkitRoot"
$CmakeArgs += "-DCMAKE_CUDA_COMPILER=$NvccPath"
$CmakeArgs += '-DGGML_CUDA_FA_ALL_QUANTS=ON'
$CmakeArgs += '-DGGML_CUDA_F16=OFF'
$CmakeArgs += '-DGGML_CUDA_GRAPHS=OFF'
$CmakeArgs += '-DGGML_CUDA_FORCE_CUBLAS=OFF'
$CmakeArgs += '-DGGML_CUDA_PEER_MAX_BATCH_SIZE=8192'
if ($CudaArch) {
# Validate nvcc actually supports this architecture
if (Test-NvccArchSupport -NvccExe $NvccPath -Arch $CudaArch) {