You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Additionally, this does not seem to cause failures in the Dynamo runtime (not caught by pass_through_build_failures), and it appears both with and without the experimental runtime.
PyTorch Version (e.g. 1.0): 2.1.0.dev20230620+cu118
TensorRT Version: 8.6.1
Additional context
This error no longer appears when we apply the @fake_tensor_unsupported flag to the backends, as was removed in #1955. It is unclear whether this is the direct cause of the bug, however.
Additionally, this bug seems to appear only sometimes, and not consistently.
The text was updated successfully, but these errors were encountered:
Bug Description
When compiling GPT-2 with Dynamo compile, the following error is encountered:
Additionally, this does not seem to cause failures in the Dynamo runtime (not caught by
pass_through_build_failures
), and it appears both with and without the experimental runtime.To Reproduce
Expected behavior
The model should not encounter TRT errors while compiling.
Environment
2.1.0.dev20230620+cu118
8.6.1
Additional context
This error no longer appears when we apply the
@fake_tensor_unsupported
flag to the backends, as was removed in #1955. It is unclear whether this is the direct cause of the bug, however.Additionally, this bug seems to appear only sometimes, and not consistently.
The text was updated successfully, but these errors were encountered: