Skip to content

Conversation

@leo0519
Copy link
Collaborator

@leo0519 leo0519 commented Oct 31, 2022

PR types

Bug fixes

PR changes

Others

Describe

Fix the Paddle-TRT UT failures

  1. test_trt_convert_elementwise
  2. test_trt_convert_group_norm
  3. test_trt_convert_pool2d

@paddle-bot
Copy link

paddle-bot bot commented Oct 31, 2022

你的PR提交成功,感谢你对开源项目的贡献!
请关注后续CI自动化测试结果,详情请参考Paddle-CI手册
Your PR has been submitted. Thanks for your contribution!
Please wait for the result of CI firstly. See Paddle CI Manual for details.

@leo0519 leo0519 force-pushed the fix-trt-ut-failure branch from 7fb38d4 to 7abbdf3 Compare November 1, 2022 01:47
@Wangzheee Wangzheee merged commit 623dce8 into PaddlePaddle:develop Nov 2, 2022
zlsh80826 pushed a commit to zlsh80826/Paddle that referenced this pull request Nov 23, 2022
qingqing01 pushed a commit that referenced this pull request Nov 28, 2022
* Reduce squeeze2_matmul_fuse_pass, flattent tests time (#47098)

* Add missing fp32 config and reduce the testing combination

* Reduce trt matmul pass test max examples

* Loose TRT fp16 tests tolerance (#47100)

* Loose TRT half test tolerance to 1e-3 (#47101)

* Loose TRT half test tolerance to 1e-3 (#47106)

* Update distributed_strategy.proto (#46531)

* Close popen pipe after used (#47053)

* Add launch_bounds (#47285)

* Fix TRT UT failures (#47488)

* Format cherry-picked commits

* CudnnNormConvolution is no longer supported on NVIDIA Hopper GPUs (#48203)

* Skip tests that use fused_ops on H100

* Add error message to FusedOps on H100

Co-authored-by: Shijie <[email protected]>
Co-authored-by: Leo Chen <[email protected]>
Co-authored-by: Tian Zheng <[email protected]>
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

contributor External developers NVIDIA

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants