21 lines
644 B
Bash
21 lines
644 B
Bash
|
|
#!/usr/bin/env bash
|
||
|
|
set -euo pipefail
|
||
|
|
|
||
|
|
SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
|
||
|
|
REPO="$(cd "$SCRIPT_DIR/../.." && pwd)"
|
||
|
|
IMAGE="${IMAGE:-aha-l2a-qwen3-repro:torch2.9.1-cu128}"
|
||
|
|
GPU_COUNT="$(nvidia-smi -L | wc -l)"
|
||
|
|
if [[ "$GPU_COUNT" -lt 1 ]]; then
|
||
|
|
echo "At least one NVIDIA GPU is required." >&2
|
||
|
|
exit 2
|
||
|
|
fi
|
||
|
|
GPU_LIST="$(seq -s, 0 $((GPU_COUNT - 1)))"
|
||
|
|
|
||
|
|
docker build -t "$IMAGE" -f "$REPO/recipe/Dockerfile" "$REPO/recipe"
|
||
|
|
docker run --rm --gpus all --ipc=host \
|
||
|
|
--ulimit memlock=-1 --ulimit stack=67108864 \
|
||
|
|
-e GPU_LIST="$GPU_LIST" \
|
||
|
|
-v "$REPO:/workspace" \
|
||
|
|
-w /workspace/recipe \
|
||
|
|
"$IMAGE" bash scripts/eval_sweep.sh
|