Uploaded image for project: 'AI Platform Core Components'
  1. AI Platform Core Components
  2. AIPCC-8939

[QA][PyTorch UT][CPU, sGPU] inductor/test_torchinductor_codegen_dynamic_shapes.py - DynamicShapesCodegenGPUTests failure

XMLWordPrintable

    • Icon: Bug Bug
    • Resolution: Unresolved
    • Icon: Major Major
    • None
    • None
    • PyTorch
    • False
    • Hide

      None

      Show
      None
    • False

      Description

      Summary: Test for PDL template and delay with dynamic shapes failing on CPU and sGPU platforms.

      Test Class: inductor/test_torchinductor_codegen_dynamic_shapes.py::DynamicShapesCodegenGPUTests
      Number of Failing Tests: 1
      Platform: CPU, sGPU (CUDA)
      Test Type: Unit Test

      Version Information:

      • PyTorch Commit: 6bdd8c9
      • Branch: main
      • Test Date: 2026-01-14
      • Sprint: Sprint 24

      Failure Pattern:
      Single root cause - launch_pdl metadata not found in generated code

      Common Error:
      code
      RuntimeError: Expected to find "'launch_pdl': True" but did not find it
      code

      Failing Tests:
      1. test_pdl_template_and_delay_dynamic_shapes_cuda

      Steps to Reproduce:
      code
      TEST_CONFIG=cpu python3 test/run_test.py -i inductor/test_torchinductor_codegen_dynamic_shapes -k test_pdl_template_and_delay_dynamic_shapes_cuda
      code

      Expected Result:
      Test should pass with correct PDL metadata in generated Triton code

      Actual Result:
      Test fails because generated code is missing launch_pdl metadata

      Priority: P2

              Unassigned Unassigned
              pytorch-engineering PyTorch Engineering
              Votes:
              0 Vote for this issue
              Watchers:
              1 Start watching this issue

                Created:
                Updated: