Skip to content
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

Jump to bottom

Bump up CUDA version used for tests #5100

Merged
merged 2 commits into from
Nov 6, 2023
Merged

Bump up CUDA version used for tests #5100

merged 2 commits into from
Nov 6, 2023

Conversation

JanuszL
Copy link
Contributor

@JanuszL JanuszL commented Oct 16, 2023 •
edited
Loading

  • disable MXNet tests are MXNet is no longer
    actively developed
  • extend support for DLPack capsules that provide
    strides collapsing dimensions
  • updates TSM PaddlePaddle example to the latest API
  • removes SSD PaddlePaddle example as it uses many no longer
    supported functions (SSD specific)

Category:

Other (e.g. Documentation, Tests, Configuration)

Description:

  • disable MXNet tests are MXNet is no longer
    actively developed
  • extend support for DLPack capsules that provide
    strides collapsing dimensions
  • updates TSM PaddlePaddle example to the latest API
  • removes SSD PaddlePaddle example as it uses many no longer
    supported functions (SSD specific)

Additional information:

Affected modules and functionalities:

  • qa/setup_packages.py

Key points relevant for the review:

Tests:

  • Existing tests apply
    • all python related
  • New tests added
    • Python tests
    • GTests
    • Benchmark
    • Other
  • N/A

Checklist

Documentation

  • Existing documentation applies
  • Documentation updated
    • Docstring
    • Doxygen
    • RST
    • Jupyter
    • Other
  • N/A

DALI team only

Requirements

  • Implements new requirements
  • Affects existing requirements
  • N/A

REQ IDs: N/A

JIRA TASK: N/A

@JanuszL JanuszL marked this pull request as draft October 16, 2023 18:22
@JanuszL JanuszL changed the title Bump up CUDA version used for tests [WIP] Bump up CUDA version used for tests Oct 16, 2023
@JanuszL JanuszL force-pushed the bump_up_cuda_test_version branch 2 times, most recently from 49df693 to b37b2c8 Compare October 23, 2023 11:24
@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10395646]: BUILD STARTED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10395646]: BUILD FAILED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10397153]: BUILD STARTED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10397721]: BUILD STARTED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10397153]: BUILD FAILED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10398803]: BUILD STARTED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10398803]: BUILD FAILED

@JanuszL JanuszL force-pushed the bump_up_cuda_test_version branch 2 times, most recently from 4527d2a to 1491ba0 Compare October 24, 2023 08:54
@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10409424]: BUILD STARTED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10409424]: BUILD FAILED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10413978]: BUILD STARTED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10413978]: BUILD PASSED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10422882]: BUILD STARTED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10422882]: BUILD FAILED

@JanuszL JanuszL force-pushed the bump_up_cuda_test_version branch 3 times, most recently from 1da40c8 to 5c33c7f Compare October 25, 2023 22:06
@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10442866]: BUILD STARTED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10449721]: BUILD STARTED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10442866]: BUILD FAILED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10449721]: BUILD FAILED

@JanuszL
Bump up CUDA version used for tests
6f8ef62 
- disable MXNet tests are MXNet is no longer
  actively developed
- extend support for DLPack capsules that provide
  strides collapsing dimensions
- updates TSM PaddlePaddle example to the latest API
- removes SSD PaddlePaddle example as it uses many no longer
  supported functions (SSD specific)

Signed-off-by: Janusz Lisiecki <jlisiecki@nvidia.com>
@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10474458]: BUILD STARTED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10474458]: BUILD FAILED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10474458]: BUILD PASSED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10479874]: BUILD STARTED

@JanuszL JanuszL marked this pull request as ready for review October 27, 2023 23:42
@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10479874]: BUILD PASSED

@JanuszL JanuszL changed the title [WIP] Bump up CUDA version used for tests Bump up CUDA version used for tests Oct 31, 2023
stiepan
stiepan reviewed Nov 2, 2023
View reviewed changes
dali/python/backend_impl.cc Outdated Show resolved Hide resolved
dali/test/python/test_torch_pipeline_rnnt.py Show resolved Hide resolved
docs/examples/use_cases/paddle/tsm/demo/7.mp4 Outdated Show resolved Hide resolved
docs/examples/use_cases/paddle/tsm/utils.py Outdated Show resolved Hide resolved
qa/TL0_FW_iterators/test_mxnet.sh Show resolved Hide resolved
qa/TL1_custom_src_pattern_build/test.sh Outdated Show resolved Hide resolved
qa/TL1_paddle_tsm/test.sh
@@ -17,7 +17,7 @@ do_once() {

test_body() {
out=`python infer.py -k 1 -s 15 demo`
if echo $out | grep -E "(paragliding|sticking_tongue_out)"; then
if echo $out | grep -E "(waxing_legs|paragliding)"; then
Copy link
Member

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

that's indeed a drastic change between the versions:)

Copy link
Contributor Author

@JanuszL JanuszL Nov 2, 2023 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

In CI it returns paragliding, locally I get waxing_legs. Visually examining the clip doesn't give me much clue which one is more correct or both are equally not correct (and I get different result by just updating PaddlePaddle and changing the model loading from paddle.fluid.io.load_persistables(exe, '', prog, filename=weight_path) to paddle.distributed.io.load_persistables(exe, '', prog, filename=weight_path)) :
image
image

@JanuszL
Review fixes
9584c30 
Signed-off-by: Janusz Lisiecki <jlisiecki@nvidia.com>
@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10563759]: BUILD STARTED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10563759]: BUILD FAILED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10576151]: BUILD STARTED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10576548]: BUILD STARTED

@dali-automaton
Copy link
Collaborator

CI MESSAGE: [10576151]: BUILD PASSED

@JanuszL JanuszL merged commit 5d353aa into NVIDIA:main Nov 6, 2023
4 checks passed
@JanuszL JanuszL deleted the bump_up_cuda_test_version branch November 6, 2023 19:28
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@stiepan stiepan stiepan approved these changes

@klecki klecki klecki approved these changes

Assignees

@klecki klecki

@stiepan stiepan

Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
4 participants
@JanuszL @dali-automaton @klecki @stiepan