Skip to content

Upgrade container versions for common examples #776

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
amaslenn merged 2 commits into from
Jan 12, 2026
Merged

Upgrade container versions for common examples #776

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
d7fd29a
Upgrade container versions for common examples
amaslenn Jan 12, 2026
f72a79a
Fix copyrights
amaslenn Jan 12, 2026
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions conf/common/test/dse_nccl_all_gather.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# SPDX-FileCopyrightText: NVIDIA CORPORATION & AFFILIATES
# Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
Expand All @@ -19,7 +19,7 @@ description = "all_gather"
test_template_name = "NcclTest"

[cmd_args]
"docker_image_url" = "nvcr.io#nvidia/pytorch:25.06-py3"
"docker_image_url" = "nvcr.io#nvidia/pytorch:25.12-py3"
"subtest_name" = "all_gather_perf_mpi"
"ngpus" = "1"
"minbytes" = "128"
Expand Down
4 changes: 2 additions & 2 deletions conf/common/test/nccl_test.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# SPDX-FileCopyrightText: NVIDIA CORPORATION & AFFILIATES
# Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
Expand All @@ -19,7 +19,7 @@ description = "NCCL base test configuration"
test_template_name = "NcclTest"

[cmd_args]
docker_image_url = "nvcr.io#nvidia/pytorch:25.06-py3"
docker_image_url = "nvcr.io#nvidia/pytorch:25.12-py3"
ngpus = 1
minbytes = "128"
maxbytes = "4G"
Expand Down
4 changes: 2 additions & 2 deletions conf/common/test/nccl_test_all_gather.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# SPDX-FileCopyrightText: NVIDIA CORPORATION & AFFILIATES
# Copyright (c) 2024-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright (c) 2024-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
Expand All @@ -19,7 +19,7 @@ description = "all_gather"
test_template_name = "NcclTest"

[cmd_args]
"docker_image_url" = "nvcr.io#nvidia/pytorch:25.06-py3"
"docker_image_url" = "nvcr.io#nvidia/pytorch:25.12-py3"
"subtest_name" = "all_gather_perf_mpi"
"ngpus" = "1"
"minbytes" = "128"
Expand Down
4 changes: 2 additions & 2 deletions conf/common/test/nemo_run_llama3_8b.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# SPDX-FileCopyrightText: NVIDIA CORPORATION & AFFILIATES
# Copyright (c) 2024-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright (c) 2024-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
Expand All @@ -19,7 +19,7 @@ description = "nemo_run_llama3_8b"
test_template_name = "NeMoRun"

[cmd_args]
docker_image_url = "nvcr.io#nvidia/nemo:25.09.00"
docker_image_url = "nvcr.io#nvidia/nemo:25.11.01"
task = "pretrain"
recipe_name = "cloudai_llama3_8b_recipe"

Expand Down
4 changes: 2 additions & 2 deletions conf/common/test/osu_test.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# SPDX-FileCopyrightText: NVIDIA CORPORATION & AFFILIATES
# Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
Expand All @@ -19,7 +19,7 @@ test_template_name = "OSUBench"
description = "OSU Benchmark example"

[cmd_args]
"docker_image_url" = "nvcr.io#nvidia/pytorch:25.06-py3"
"docker_image_url" = "nvcr.io#nvidia/pytorch:25.12-py3"
"benchmarks_dir" = "/opt/hpcx/ompi/tests/osu-micro-benchmarks"
"benchmark" = "osu_allreduce"
"iterations" = 10
Expand Down
4 changes: 2 additions & 2 deletions conf/common/test/ucc_test.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# SPDX-FileCopyrightText: NVIDIA CORPORATION & AFFILIATES
# Copyright (c) 2024-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright (c) 2024-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
Expand All @@ -19,4 +19,4 @@ description = "Base config for UCC tests"
test_template_name = "UCCTest"

[cmd_args]
docker_image_url = "nvcr.io#nvidia/pytorch:25.06-py3"
docker_image_url = "nvcr.io#nvidia/pytorch:25.12-py3"
4 changes: 2 additions & 2 deletions conf/common/test_scenario/dse_nemo_run_llama3_8b.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# SPDX-FileCopyrightText: NVIDIA CORPORATION & AFFILIATES
# Copyright (c) 2024-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright (c) 2024-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
Expand All @@ -26,7 +26,7 @@ description = "dse_nemo_run_llama3_8b"
test_template_name = "NeMoRun"

[Tests.cmd_args]
docker_image_url = "nvcr.io#nvidia/nemo:25.09.00"
docker_image_url = "nvcr.io#nvidia/nemo:25.11.01"
task = "pretrain"
recipe_name = "cloudai_llama3_8b_recipe"
num_layers = 32
Expand Down
4 changes: 2 additions & 2 deletions conf/common/test_scenario/nccl_test.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# SPDX-FileCopyrightText: NVIDIA CORPORATION & AFFILIATES
# Copyright (c) 2024-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright (c) 2024-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
Expand Down Expand Up @@ -68,7 +68,7 @@ description = "scatter_perf"
test_template_name = "NcclTest"

[Tests.cmd_args]
docker_image_url = "nvcr.io#nvidia/pytorch:25.06-py3"
docker_image_url = "nvcr.io#nvidia/pytorch:25.12-py3"
subtest_name = "scatter_perf_mpi"
ngpus = 1
minbytes = "128"
Expand Down
4 changes: 2 additions & 2 deletions conf/common/test_scenario/slurm_container.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# SPDX-FileCopyrightText: NVIDIA CORPORATION & AFFILIATES
# Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright (c) 2025-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
Expand All @@ -26,5 +26,5 @@ description = "NCCL alltoall via SlurmContainer"
test_template_name = "SlurmContainer"

[Tests.cmd_args]
docker_image_url = "nvcr.io#nvidia/pytorch:25.06-py3"
docker_image_url = "nvcr.io#nvidia/pytorch:25.12-py3"
cmd = "alltoall_perf_mpi --nthreads 1 --ngpus 1 --minbytes 128 --maxbytes 4G --stepbytes 1M --op sum --datatype float --root 0 --iters 100 --warmup_iters 50 --agg_iters 1 --average 1 --parallel_init 0 --check 1 --blocking 0 --cudagraph 0 --stepfactor 2"
4 changes: 2 additions & 2 deletions conf/common/test_scenario/ucc_generator_test.toml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
# SPDX-FileCopyrightText: NVIDIA CORPORATION & AFFILIATES
# Copyright (c) 2024-2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# Copyright (c) 2024-2026 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
# SPDX-License-Identifier: Apache-2.0
#
# Licensed under the Apache License, Version 2.0 (the "License");
Expand Down Expand Up @@ -30,6 +30,6 @@ extra_container_mounts = [
]

[Tests.cmd_args]
docker_image_url = "nvcr.io/nvidia/pytorch:25.09-py3"
docker_image_url = "nvcr.io/nvidia/pytorch:25.12-py3"
collective = "alltoallv"
gen = "file:name=/opt/hpcx/ucc/tools/perf/generator/input_matrices.txt"