mirror of
https://github.com/PaddlePaddle/FastDeploy.git
synced 2025-12-24 13:28:13 +08:00
[XPU]add xpu ci ep case (#4432)
* add xpu ci case * Add xDeepEP download and build steps Download and build xDeepEP before running tests. * Fix formatting and add missing sleep command * Update Docker image version in CI workflow * Modify run_ci_xpu.sh for log cleanup and error handling Clean up log files before running tests and output worker log on failure. * Enhance test_ep.py with process management and assertions Refactor test function to include process cleanup and assertions. * Replace test_fastdeploy_llm with test_fd_ep * Fix conditional statement in run_ci_xpu.sh * Update test_ep.py for string handling and formatting Fix string encoding issues and improve readability. * Rename test_ep.py to run_ep.py * Change test script from test_ep.py to run_ep.py
This commit is contained in:
@@ -176,3 +176,33 @@ if [ ${kv_block_test_exit_code} -ne 0 ]; then
|
||||
echo "kv block相关测试失败,请检查pr代码"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "============================开始EP并行测试!============================"
|
||||
sleep 5
|
||||
rm -rf log/*
|
||||
rm -f core*
|
||||
xpu-smi
|
||||
export XPU_VISIBLE_DEVICES="0,1,2,3"
|
||||
export BKCL_ENABLE_XDR=1
|
||||
export BKCL_RDMA_NICS=xgbe1,xgbe2,xgbe3,xgbe4
|
||||
export BKCL_TRACE_TOPO=1
|
||||
export BKCL_PCIE_RING=1
|
||||
export XSHMEM_MODE=1
|
||||
export XSHMEM_QP_NUM_PER_RANK=32
|
||||
export BKCL_RDMA_VERBS=1
|
||||
|
||||
wget -q https://paddle-qa.bj.bcebos.com/xpu_third_party/xDeepEP.tar.gz
|
||||
tar -xzf xDeepEP.tar.gz
|
||||
cd xDeepEP
|
||||
bash build.sh
|
||||
cd -
|
||||
|
||||
python tests/ci_use/XPU_45T/run_ep.py
|
||||
ep_exit_code=$?
|
||||
|
||||
if [ ${ep_exit_code} -ne 0 ]; then
|
||||
echo "log/workerlog.0"
|
||||
cat log/workerlog.0
|
||||
echo "EP并行 相关测试失败,请检查pr代码"
|
||||
exit 1
|
||||
fi
|
||||
|
||||
Reference in New Issue
Block a user