Skip to content
This repository has been archived by the owner on Nov 17, 2023. It is now read-only.

[v1.x] TRT test update #19296

Merged
merged 3 commits into from
Oct 12, 2020
Merged

[v1.x] TRT test update #19296

merged 3 commits into from
Oct 12, 2020

Conversation

DickJC123
Copy link
Contributor

Description

This PR includes improvements discovered during the testing of the v1.8.x branch:

  • For the test_tensorrt.py:test_tensorrt_symbol test, the explicitly set tolerances were removed for the 32-bit model test. This allows the test to pass on A100 by allowing the framework to detect the A100 context and choose the relaxed tolerance appropriate for a TF32 calculation.
  • For the test_tensorrt.py:test_tensorrt_symbol_int8 test, logic was inserted to avoid running the test on GPU architectures earlier than Volta (PASCAL, MAXWELL, etc.). On PASCAL, where int8 is not supported, a message was printed, but then the test hung.
    With this PR, the test is skipped. In general, users should not attempt running TRT int8 on PASCAL GPUs or earlier.
  • Finally, a CI failure was seen in test_operator_gpu.py:test_np_mixed_precision_binary_funcs for seed MXNET_TEST_SEED=590323404. Additional repro'd failures all seemed to occur when the data shape was (). This behavior was seen and fixed in master PR [numpy] fix flaky mixed precision binary error #18660. This PR includes only the portion of that PR that skips the test when the data shape is (). The full PR should still be backported by the author to 1.x if deemed useful.

@yzhliu @Kh4L @samskalicky

Checklist

Essentials

  • [X ] PR's title starts with a category (e.g. [BUGFIX], [MODEL], [TUTORIAL], [FEATURE], [DOC], etc)
  • [X ] Changes are complete (i.e. I finished coding on this PR)
  • [X ] All changes have test coverage
  • [X ] Code is well-documented

Changes

  • Feature1, tests, (and when applicable, API doc)
  • Feature2, tests, (and when applicable, API doc)

Comments

  • If this change is a backward incompatible change, why must this change be made.
  • Interesting edge cases to note here

@mxnet-bot
Copy link

Hey @DickJC123 , Thanks for submitting the PR
All tests are already queued to run once. If tests fail, you can trigger one or more tests again with the following commands:

  • To trigger all jobs: @mxnet-bot run ci [all]
  • To trigger specific jobs: @mxnet-bot run ci [job1, job2]

CI supported jobs: [windows-gpu, centos-cpu, clang, windows-cpu, unix-cpu, unix-gpu, miscellaneous, centos-gpu, edge, website, sanity]


Note:
Only following 3 categories can trigger CI :PR Author, MXNet Committer, Jenkins Admin.
All CI tests must pass before the PR can be merged.

@DickJC123 DickJC123 changed the title Trt test update [v1.x] Trt test update Oct 6, 2020
@DickJC123 DickJC123 changed the title [v1.x] Trt test update [v1.x] TRT test update Oct 6, 2020
@szha szha merged commit 6729cf3 into apache:v1.x Oct 12, 2020
szha pushed a commit that referenced this pull request Oct 12, 2020
* Bypass test_tensorrt.py:test_tensorrt_symbol_int8 on arch < 70

* Adapt test_tensorrt.py:test_tensorrt_symbol for A100

* Fix test_numpy_op.py:test_np_mixed_precision_binary_funcs with portion of (#18660)
Sign up for free to subscribe to this conversation on GitHub. Already have an account? Sign in.
Labels
None yet
Projects
None yet
Development

Successfully merging this pull request may close these issues.

None yet

3 participants