clee2000

Results 54 comments of clee2000

@clee2000 has imported this pull request. If you are a Meta employee, you can view this diff [on Phabricator](https://www.internalfb.com/diff/D55448636).

@pytorchbot revert -m "test test/inductor/test_cudagraph_trees.py::CudaGraphTreeTests::test_fallback_to_eager_if_recompiling_too_many_times is failing https://github.com/pytorch/pytorch/actions/runs/9933628108/job/27477785946 https://hud.pytorch.org/pytorch/pytorch/commit/1bc390c5f5ac065c156f55f4eceed267ecc67b41. Test was introduced by fa5f5727484d78aa2ed8668c11550431bd415f5c which is before the merge base" -c landarce

> @huydhn hmmm so what exactly do I need to do? If you do mean to use >6GB of memory, do something like https://github.com/pytorch/pytorch/pull/126399 > (Note for @clee2000, I remember...

AI me: compile a list of reusable actions that don't have testing

Adding https://github.com/pytorch/pytorch/pull/115070 for general pytest tracking: "Pytest replaces sys.stdout/stderr by TextIOWrapper instances which do not support `fileno()`" which might affect some test cases

linter has also been merged https://github.com/pytorch/pytorch/pull/114882

@pytorchbot revert -m "I think dr ci is wrong and the windows build failure is real https://hud.pytorch.org/pytorch/pytorch/commit/e2f081837f4276c1a6a37739bd28157f62004a06 https://github.com/pytorch/pytorch/actions/runs/9216826622/job/25357819877" -c weird

@pytorchbot revert -m "sorry the Dr CI fix hasn't been merged yet and its still failing https://hud.pytorch.org/pytorch/pytorch/commit/5e69e11d098a2cfccc8a59377c431e9c71cab9a8 https://github.com/pytorch/pytorch/actions/runs/9228887299/job/25393895252" -c weird