pytorch / pytorch/TensorRT

🐛 [Bug] [NGC] L2 Dynamo Test on B200 and H100

Open
#3,859 0 comments 0 reactions 2 assignees View on GitHub

@peri044 is already working on this.

Since Oct 14, 2025.

bug story: CI/CD & Testing Infrastructure
Dominant language
Python
Stars
3k
Forks
410
Avg merge
3d 18h
Merged PRs (30d)
78

Description

Bug:

FAILED llm/test_llm_models.py::test_llm_decoder_layer[FP16] - AssertionError
FAILED llm/test_llm_models.py::test_llm_decoder_layer[BF16] - AssertionError

TRT 10.13.3.9
Pytorch 2.10.0a0+b558c986e8

Passes on A100.
Error:

2025-10-11T04:31:34.722267Z 01O ERROR    torch_tensorrt [TensorRT Conversion Context]:logging.py:22 Error Code: 9: Skipping tactic 0x0000000000000000 due to exception [myelin_graph.h:attachExceptionMsgToGraph:1146] MyelinCheckException: bb.cpp:138: CHECK(op->parent() == this || op->parent() == nullptr) failed.  In compileGraph at optimizer/myelin/codeGenerator.cpp:1425
2025-10-11T04:31:34.722270Z 01O ERROR    torch_tensorrt [TensorRT Conversion Context]:logging.py:22 IBuilder::buildSerializedNetwork: Error Code 10: Internal Error (Could not find any implementation for node {ForeignNode[[SLICE]-[aten_ops.slice.Tensor]-[model/slice_1]...[SHUFFLE]-[aten_ops._reshape_copy.default]-[lm_head/_reshape_copy_31]]}. In computeCosts at optimizer/common/tactic/optimizer.cpp:4115)

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.