Popular repositories Loading
-
TensorRT
TensorRT PublicForked from NVIDIA/TensorRT
TensorRT is a C++ library for high performance inference on NVIDIA GPUs and deep learning accelerators.
C++ 1
-
tensorflow
tensorflow PublicForked from tensorflow/tensorflow
An Open Source Machine Learning Framework for Everyone
C++
-
onnx-tensorrt
onnx-tensorrt PublicForked from onnx/onnx-tensorrt
ONNX-TensorRT: TensorRT backend for ONNX
C++
-
onnxruntime
onnxruntime PublicForked from microsoft/onnxruntime
ONNX Runtime: cross-platform, high performance scoring engine for ML models
C++
-
tensorflow-onnx
tensorflow-onnx PublicForked from onnx/tensorflow-onnx
Convert TensorFlow, Keras, Tensorflow.js and Tflite models to ONNX
Jupyter Notebook
616 contributions in the last year
Day of Week | March Mar | April Apr | May May | June Jun | July Jul | August Aug | September Sep | October Oct | November Nov | December Dec | January Jan | February Feb | March Mar | ||||||||||||||||||||||||||||||||||||||||
Sunday Sun | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Monday Mon | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Tuesday Tue | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Wednesday Wed | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Thursday Thu | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Friday Fri | |||||||||||||||||||||||||||||||||||||||||||||||||||||
Saturday Sat |
Contribution activity
March 2025
Created 9 commits in 1 repository
Created a pull request in NVIDIA/TensorRT-Incubator that received 4 comments
Updates default TensorRT version to 10.9
Updates the default version we compile against to 10.9. Also corrects the build number to match the latest release.
Opened 16 other pull requests in 1 repository
NVIDIA/TensorRT-Incubator
1
open
14
merged
1
closed
-
Adds extra debugging information
This contribution was made on Mar 21
-
Makes DefaultParameter not tensor, Adds forward for Module, checks fo…
This contribution was made on Mar 19
-
Adds support for variadic arguments in
tp.compile
This contribution was made on Mar 18 -
Enables I4 in shape and I8 in where
This contribution was made on Mar 18
-
Adds back guides, overhauls data type constraint testing
This contribution was made on Mar 18
-
Enables more data types in various operations
This contribution was made on Mar 18
-
Improves slice error messages for unsupported types
This contribution was made on Mar 13
-
Various bug fixes
This contribution was made on Mar 13
-
Removes eager mode caching
This contribution was made on Mar 13
-
Enables BF16 in pooling
This contribution was made on Mar 11
-
Moves I64 shape test to TRT10 directory
This contribution was made on Mar 6
-
Allows scalars in unary operations
This contribution was made on Mar 6
-
Corrects resize validation for dynamic shapes
This contribution was made on Mar 6
-
Allows I64 tensors in
tensorrt.shape
This contribution was made on Mar 6 -
Adds layer checks to prevent nullptr dereferences
This contribution was made on Mar 5
-
Updates TensorRT outlining to propagate shape profile attributes
This contribution was made on Mar 3
Reviewed 12 pull requests in 2 repositories
NVIDIA/TensorRT-Incubator
11 pull requests
-
Document tensor.eval, tolist
This contribution was made on Mar 20
-
Enables more data types in various operations
This contribution was made on Mar 18
-
Add support for TensorRT Quickly Deployable Plugins
This contribution was made on Mar 17
-
Improves slice error messages for unsupported types
This contribution was made on Mar 13
-
Document eval, tolist
This contribution was made on Mar 13
-
Updates TensorRT outlining to propagate shape profile attributes
This contribution was made on Mar 12
-
Enable QDQ related tests, enforce scale to be constant
This contribution was made on Mar 12
-
Allows I64 tensors in
tensorrt.shape
This contribution was made on Mar 6 -
[build_tools] Add cmake preset for clang python wheel release
This contribution was made on Mar 5
-
Adds
cast
totensorrt
dialectThis contribution was made on Mar 5 -
Adds layer checks to prevent nullptr dereferences
This contribution was made on Mar 5
triton-inference-server/tutorials
1 pull request
-
docs: Add EAGLE/SpS Speculative Decoding support with vLLM
This contribution was made on Mar 13
Created an issue in NVIDIA/TensorRT-Incubator that received 1 comment
allclose
seems to incorrectly report mismatches
In many cases (e.g. #569), it seems that allclose
reports a mismatch in cases where the tensors compare equal if they are evaluated first. This see…
Opened 7 other issues in 1 repository
NVIDIA/TensorRT-Incubator
7
open
-
Cannot use
tensorrt.broadcast
with int8 inputsThis contribution was made on Mar 18 -
quantize
to int4 does not work with constantsThis contribution was made on Mar 18 -
Add support for multiple devices
This contribution was made on Mar 14
-
Re-implement eager mode caching
This contribution was made on Mar 13
-
Enable
tensorrt.assertion
in TripyThis contribution was made on Mar 12 -
Some
Conv
tests failing with BF16This contribution was made on Mar 12 -
ConvTranspose does not work with BF16
This contribution was made on Mar 11