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
481 B
Bash
Executable File
21 lines
481 B
Bash
Executable File
#!/bin/bash
|
|
set -e
|
|
|
|
backend_dir=$(dirname $0)
|
|
|
|
for cuda_version in 12 13; do
|
|
grep -qx "flash-attn" "$backend_dir/requirements-cublas${cuda_version}-after.txt"
|
|
done
|
|
|
|
grep -q 'BUILD_PROFILE.*cublas13' "$backend_dir/install.sh"
|
|
grep -q 'MAX_JOBS.*1' "$backend_dir/install.sh"
|
|
grep -q 'NVCC_THREADS.*1' "$backend_dir/install.sh"
|
|
|
|
if [ -d $backend_dir/common ]; then
|
|
source $backend_dir/common/libbackend.sh
|
|
else
|
|
source $backend_dir/../common/libbackend.sh
|
|
fi
|
|
|
|
runUnittests
|