d5f72835e6
<!-- Thanks for sending a pull request! BEFORE SUBMITTING, PLEASE READ https://docs.vllm.ai/en/latest/contributing/overview.html --> ### What this PR does / why we need it? <!-- - Please clarify what changes you are proposing. The purpose of this section is to outline the changes and how this PR fixes the issue. If possible, please consider writing useful notes for better and faster reviews in your PR. - Please clarify why the changes are needed. For instance, the use case and bug description. - Fixes # --> This pull request introduces a new custom operator `aclnnMoeInitRoutingCustom` for Mixture-of-Experts models. It can be replaced by `aclnnMoeInitRoutingV3` once CANN 8.5 becomes available. ### Does this PR introduce _any_ user-facing change? <!-- Note that it means *any* user-facing change including all aspects such as API, interface or other behavior changes. Documentation-only updates are not considered user-facing changes. --> No. ### How was this patch tested? <!-- CI passed with new added/existing test. If it was tested in a way different from regular unit tests, please clarify how you tested step by step, ideally copy and paste-able, so that other reviewers can test and check, and descendants can verify in the future. If tests were not added, please describe why they were not added and/or why it was difficult to add. --> --------- Signed-off-by: jiazhengyi <jiazhengyi@huawei.com> Signed-off-by: Chenxi Qian <chenxi.qian.cq@outlook.com> Co-authored-by: jiazhengyi <jiazhengyi@huawei.com> Co-authored-by: Chenxi Qian <chenxi.qian.cq@outlook.com>
91 lines
3.2 KiB
Bash
91 lines
3.2 KiB
Bash
#!/bin/bash
|
|
|
|
ROOT_DIR=$1
|
|
SOC_VERSION=$2
|
|
|
|
if [[ "$SOC_VERSION" =~ ^ascend310 ]]; then
|
|
# ASCEND310P series
|
|
# currently, no custom aclnn ops for ASCEND310 series
|
|
# CUSTOM_OPS=""
|
|
# SOC_ARG="ascend310p"
|
|
exit 0
|
|
elif [[ "$SOC_VERSION" =~ ^ascend910b ]]; then
|
|
# ASCEND910B (A2) series
|
|
# depdendency: catlass
|
|
git config --global --add safe.directory "$ROOT_DIR"
|
|
CATLASS_PATH=${ROOT_DIR}/csrc/third_party/catlass/include
|
|
if [[ ! -d "${CATLASS_PATH}" ]]; then
|
|
echo "depdendency catlass is missing, try to fetch it..."
|
|
if ! git submodule update --init --recursive; then
|
|
echo "fetch failed"
|
|
exit 1
|
|
fi
|
|
fi
|
|
ABSOLUTE_CATLASS_PATH=$(cd "${CATLASS_PATH}" && pwd)
|
|
export CPATH=${ABSOLUTE_CATLASS_PATH}:${CPATH}
|
|
|
|
CUSTOM_OPS="grouped_matmul_swiglu_quant_weight_nz_tensor_list;lightning_indexer;sparse_flash_attention;matmul_allreduce_add_rmsnorm;moe_init_routing_custom"
|
|
SOC_ARG="ascend910b"
|
|
elif [[ "$SOC_VERSION" =~ ^ascend910_93 ]]; then
|
|
# ASCEND910C (A3) series
|
|
# depdendency: catlass
|
|
git config --global --add safe.directory "$ROOT_DIR"
|
|
CATLASS_PATH=${ROOT_DIR}/csrc/third_party/catlass/include
|
|
if [[ ! -d "${CATLASS_PATH}" ]]; then
|
|
echo "depdendency catlass is missing, try to fetch it..."
|
|
if ! git submodule update --init --recursive; then
|
|
echo "fetch failed"
|
|
exit 1
|
|
fi
|
|
fi
|
|
# depdendency: cann-toolkit file moe_distribute_base.h
|
|
HCCL_STRUCT_FILE_PATH=$(find -L "${ASCEND_TOOLKIT_HOME}" -name "moe_distribute_base.h" 2>/dev/null | head -n1)
|
|
if [ -z "$HCCL_STRUCT_FILE_PATH" ]; then
|
|
echo "cannot find moe_distribute_base.h file in CANN env"
|
|
exit 1
|
|
fi
|
|
# for dispatch_gmm_combine_decode
|
|
yes | cp "${HCCL_STRUCT_FILE_PATH}" "${ROOT_DIR}/csrc/utils/inc/kernel"
|
|
# for dispatch_ffn_combine
|
|
SCRIPT_DIR=$(cd "$(dirname "$0")" && pwd)
|
|
TARGET_DIR="$SCRIPT_DIR/dispatch_ffn_combine/op_kernel/utils/"
|
|
TARGET_FILE="$TARGET_DIR/$(basename "$HCCL_STRUCT_FILE_PATH")"
|
|
|
|
echo "*************************************"
|
|
echo $HCCL_STRUCT_FILE_PATH
|
|
echo "$TARGET_DIR"
|
|
cp "$HCCL_STRUCT_FILE_PATH" "$TARGET_DIR"
|
|
|
|
sed -i 's/struct HcclOpResParam {/struct HcclOpResParamCustom {/g' "$TARGET_FILE"
|
|
sed -i 's/struct HcclRankRelationResV2 {/struct HcclRankRelationResV2Custom {/g' "$TARGET_FILE"
|
|
|
|
CUSTOM_OPS_ARRAY=(
|
|
"grouped_matmul_swiglu_quant_weight_nz_tensor_list"
|
|
"lightning_indexer"
|
|
"sparse_flash_attention"
|
|
"dispatch_ffn_combine"
|
|
"dispatch_gmm_combine_decode"
|
|
"moe_combine_normal"
|
|
"moe_dispatch_normal"
|
|
"dispatch_layout"
|
|
"notify_dispatch"
|
|
"moe_init_routing_custom"
|
|
)
|
|
CUSTOM_OPS=$(IFS=';'; echo "${CUSTOM_OPS_ARRAY[*]}")
|
|
SOC_ARG="ascend910_93"
|
|
else
|
|
# others
|
|
# currently, no custom aclnn ops for other series
|
|
exit 0
|
|
fi
|
|
|
|
|
|
# build custom ops
|
|
cd csrc
|
|
rm -rf build output
|
|
echo "building custom ops $CUSTOM_OPS for $SOC_VERSION"
|
|
bash build.sh -n "$CUSTOM_OPS" -c "$SOC_ARG"
|
|
|
|
# install custom ops to vllm_ascend/_cann_ops_custom
|
|
./output/CANN-custom_ops*.run --install-path=$ROOT_DIR/vllm_ascend/_cann_ops_custom
|