-
Notifications
You must be signed in to change notification settings - Fork 0
/
ci.yml
47 lines (41 loc) · 1.4 KB
/
ci.yml
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
# Copyright (c) 2018-2022, NVIDIA CORPORATION. All rights reserved.
#
# 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.
include:
- cosmoflow/pytorch/ci_nightly.yml
- cosmoflow/pytorch/ci_dryrun.yml
variables:
BENCHMARK: cosmoflow
FRAMEWORK: pytorch
BENCHMARK_PATH: cosmoflow/pytorch
MODEL_NAME: Cosmoflow
TIME_TAGS: 0
NVTX_FLAG: 0
cosmoflow_pytorch:
extends: .build_job
.cosmoflow_pytorch_dgxa100_job:
needs: [ cosmoflow_pytorch ]
extends: .dgxa100_job
# NEXP defined from,
# https://github.com/mlcommons/logging/blob/master/mlperf_logging/benchmark_meta.py#L19: cosmoflow needs N=10 strong scaling runs, we do 2N
.dr_strong_cosmoflow_pytorch_dgxa100_job:
needs: [ cosmoflow_pytorch ]
variables:
NEXP: 10
extends: .dr_dgxa100_job
# weak scaling is always just one experiment
.dr_weak_cosmoflow_pytorch_dgxa100_job:
needs: [ cosmoflow_pytorch ]
variables:
NEXP: 1
extends: .dr_dgxa100_job