Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

feat: Add support for TorchTensorRTModule in Dynamo [1 / x] #2003

Merged
merged 3 commits into from
Jul 7, 2023
Merged

feat: Add support for TorchTensorRTModule in Dynamo [1 / x] #2003

merged 3 commits into from
Jul 7, 2023

Commits on Jul 7, 2023

  1. feat: Add support for TorchTensorRTModule in Dynamo 

    - Rename `TRTModuleNext` to `TorchTensorRTModule` across the repository,
and move the source directory to `dynamo`
- Update imports across the repository
- Refactor `convert_module` code to support conversion to a
`TorchTensorRTModule`
- Add logging information about which runtime is being used in Dynamo
compile
- Add tests for `TorchTensorRTModule` functionality in Dynamo
    @gs-olive
    gs-olive committed Jul 7, 2023
    Configuration menu
    Copy the full SHA
    a225769 View commit details
    Browse the repository at this point in the history

  2. fix: Add new TRT 8.6 features to Dynamo compile [3 / x] (#1973)

    @gs-olive
    gs-olive committed Jul 7, 2023
    Configuration menu
    Copy the full SHA
    1c8d93a View commit details
    Browse the repository at this point in the history

  3. feat: Automatically detect C++ dependency presence 

    - Default automatically to test for presence of C++ dependency and use
appropriate runtime if not specified by the user
- Improve test timing for TRT Backend testing, which now utilizes C++
runtime
    @gs-olive
    gs-olive committed Jul 7, 2023
    Configuration menu
    Copy the full SHA
    1756b12 View commit details
    Browse the repository at this point in the history