fix(common): robust XPU platform auto-detection

Capture xpu-smi output before grepping to avoid SIGPIPE failures under
set -o pipefail when grep -q exits early.
This commit is contained in:
Quantong Qiu 2026-07-08 05:50:42 +00:00
parent e72e34c2f7
commit f0d4c4753b

View File

@ -9,7 +9,15 @@ ROOT_DIR="$(cd "${_PLATFORM_DIR}/../.." && pwd)"
# Auto-detect platform if not set.
if [[ -z "${PLATFORM:-}" ]]; then
if lspci 2>/dev/null | grep -qiE "XPU|Kunlun"; then
# Capture xpu-smi output first; piping it directly can trigger SIGPIPE under
# pipefail when grep -q exits early.
_XPU_SMI_OUT=""
if command -v xpu-smi >/dev/null 2>&1; then
_XPU_SMI_OUT=$(xpu-smi 2>/dev/null || true)
fi
if [[ -n "$_XPU_SMI_OUT" ]] && grep -qiE "P800|Kunlun" <<< "$_XPU_SMI_OUT"; then
PLATFORM="kunlun_p800"
elif lspci 2>/dev/null | grep -qiE "XPU|Kunlun"; then
PLATFORM="kunlun_p800"
elif command -v nvidia-smi >/dev/null 2>&1; then
PLATFORM="nvidia_h200"
@ -17,6 +25,7 @@ if [[ -z "${PLATFORM:-}" ]]; then
echo "ERROR: Could not auto-detect PLATFORM. Set PLATFORM env var explicitly." >&2
exit 1
fi
unset _XPU_SMI_OUT
echo "Auto-detected platform: ${PLATFORM}"
fi