Focusing
Deep Learning @NVIDIA
- California, USA
- https://www.linkedin.com/in/dheerajperi/
Highlights
- Pro
Block or Report
Block or report peri044
Report abuse
Contact GitHub support about this user’s behavior. Learn more about reporting abuse.
Report abusePinned
-
-
ppgn Public
Forked from Evolving-AI-Lab/ppgn
Code for paper "Plug and Play Generative Networks"
Python
259 contributions in the last year
Contribution activity
August 2022
Created 6 commits in 1 repository
Created a pull request in pytorch/TensorRT that received 8 comments
fix(//core/converters): Handle dtype mismatch in elementwise ops
Description Handle dtype mismatch in elementwise ops Type of change Bug fix (non-breaking change which fixes an issue) Checklist: My code follo…
+13
−7
•
8
comments
Opened 3 other pull requests in 1 repository
Reviewed 9 pull requests in 1 repository
pytorch/TensorRT
9 pull requests
- chore: Fix data loader issues and nox file paths
- [feat] Add automatic type promotion to element-wise ops
- feat: support for grouped inputs
- Update PTQ example to fix new compile_spec requirements
- [feat] Add support for integers in aten::abs converter (#35)
- fix: fix the "schema not found for node" error
- [FX] disable 2 of conv3d and type_as tests
- chore: Apply linting and ignore new bazel dirs
- Fix typo in EfficientNet-example
Created an issue in pytorch/TensorRT that received 10 comments
✨ [Feature] Perform constant folding of operations in the graph if nodes can be evaluated at compile time
Is your feature request related to a problem? Please describe.
%28 : int = aten::size(%22, %27)
...
%31 : Tensor[] = tensorrt::execute_engine(%30, …
10
comments


