mirror of
https://github.com/mudler/LocalAI.git
synced 2026-09-12 22:33:54 -04:00
Ettore Di Giacinto
1dfa25e681
The CUDA 13 FlashAttention build still exhausts hosted-runner memory with a single ninja worker because nvcc can compile multiple threads internally. Limit nvcc to one thread for that profile and guard the setting in the backend test script. Assisted-by: Codex:gpt-5 Signed-off-by: Ettore Di Giacinto <mudler@localai.io>
21 lines
539 B
Bash
Executable File
21 lines
539 B
Bash
Executable File
#!/bin/bash
|
|
set -e
|
|
|
|
EXTRA_PIP_INSTALL_FLAGS="--no-build-isolation"
|
|
|
|
backend_dir=$(dirname $0)
|
|
if [ -d $backend_dir/common ]; then
|
|
source $backend_dir/common/libbackend.sh
|
|
else
|
|
source $backend_dir/../common/libbackend.sh
|
|
fi
|
|
|
|
# CUDA 13 has no prebuilt FlashAttention wheel, so the fallback source build
|
|
# exceeds the CI runner's memory when ninja compiles multiple units at once.
|
|
if [ "x${BUILD_PROFILE}" = "xcublas13" ]; then
|
|
export MAX_JOBS="${MAX_JOBS:-1}"
|
|
export NVCC_THREADS="${NVCC_THREADS:-1}"
|
|
fi
|
|
|
|
installRequirements
|