36 lines
1.3 KiB
Bash
36 lines
1.3 KiB
Bash
#
|
|
# Copyright 2016 The BigDL Authors.
|
|
#
|
|
# Licensed under the Apache License, Version 2.0 (the "License");
|
|
# you may not use this file except in compliance with the License.
|
|
# You may obtain a copy of the License at
|
|
#
|
|
# http://www.apache.org/licenses/LICENSE-2.0
|
|
#
|
|
# Unless required by applicable law or agreed to in writing, software
|
|
# distributed under the License is distributed on an "AS IS" BASIS,
|
|
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
|
# See the License for the specific language governing permissions and
|
|
# limitations under the License.
|
|
#
|
|
|
|
export MASTER_ADDR=127.0.0.1
|
|
export FI_PROVIDER=tcp
|
|
export CCL_ATL_TRANSPORT=ofi
|
|
export CCL_ZE_IPC_EXCHANGE=sockets
|
|
export no_proxy=localhost
|
|
|
|
export LD_PRELOAD=${LD_PRELOAD}:${CONDA_PREFIX}/lib/libtcmalloc.so:${LD_PRELOAD}
|
|
basekit_root=/opt/intel/oneapi
|
|
source $basekit_root/setvars.sh --force
|
|
source $basekit_root/ccl/latest/env/vars.sh --force
|
|
|
|
NUM_GPUS=2 # number of used GPU
|
|
export USE_XETLA=OFF
|
|
export SYCL_PI_LEVEL_ZERO_USE_IMMEDIATE_COMMANDLISTS=2
|
|
export TORCH_LLM_ALLREDUCE=0
|
|
|
|
export WORLD_SIZE=2
|
|
|
|
mpirun -np $NUM_GPUS --prepend-rank \
|
|
python serving.py --repo-id-or-model-path YOUR_REPO_ID_OR_MODEL_PATH --low-bit 'fp8' --port 8000 --max-num-seqs 8 --max-num-batched-tokens 8192
|