Releases: onnx/onnx-tensorrt
Releases · onnx/onnx-tensorrt
ONNX-TensorRT 8.2 GA Release
Added
See the 8.2 EA release notes for new features added in TensorRT 8.2.
Fixes
- Removed duplicate constant layer checks that caused some performance regressions
- Fixed expand dynamic shape calculations
- Added parser-side checks for Scatter layer support
ONNX-TensorRT 8.2 EA Release
Added
- Added support for the following ONNX operators:
- Einsum
- IsNan
- GatherND
- Scatter
- ScatterElements
- ScatterND
- Sign
- Round
Updated
- Updated
Gather
andGatherElements
implementations to natively support negative indices - Updated
Pad
layer to support ND padding, along withedge
andreflect
padding mode support - Updated
If
layer with general performance improvements.
ONNX-TensorRT 8.0 Release
Added
- Rehauled resize operator, now fully supporting the following modes:
- Coordinate Transformation modes:
half_pixel
,pytorch_half_pixel
,tf_half_pixel_for_nn
,asymmetric
, andalign_corners
- Modes:
nearest
,linear
- Nearest Modes:
floor
,ceil
,round_prefer_floor
,round_prefer_ceil
- Coordinate Transformation modes:
- QuantizeLinear/DequantizeLinear updates:
- Added support for tensor scales
- Added support for per-axis quantization
- Added support for multi-input ConvTranpose
- Added support for generic 2D padding
- Added experimental support for
NonMaxSuppression
Updated
- Moved
RefitMap
API to core TensorRT. - Added Datatype column to operators.md
For more information on the TensorRT 8.0 release, see the release notes.
ONNX-TensorRT 21.05 Release
Added
- Added support for InstanceNormalization on 5D tensors
- Added library only build target #659
- Added support for negative gather indices #681
- Added support for
DOUBLE
-typed inputs and weights through downcast to float #674 - Added support for optional plugin fields in FallbackPlugin path #676
Updated
- Updated license #657
Fixes
- Fixed index offset calculation in GatherElements #675
- Clarified dynamic shape support for ReverseSequence
ONNX-TensorRT 21.03 Release
This is the release of ONNX-TensorRT that is used in the 21.03 NVIDIA NGC containers.
Changes
Added
- Added opset13 support for
SoftMax
,LogSoftmax
,Squeeze
, andUnsqueeze
- Added support for the
EyeLike
operator - Added support for the
GatherElements
operator
ONNX-TensorRT 21.02 Release
This is the release of ONNX-TensorRT that is used in the 21.02 NVIDIA NGC containers.
Changes
Added
- Added support for the
ReverseSequence
operator #590 - Updated
parse()
andsupportsModel()
API calls with an optionalmodel_path
parameter to support models with external weights #621 - Added support for the
Celu
operator - Added support for the
CumSum
operator - Added support for the
LessOrEqual
operator - Added support for the
LpNormalization
operator - Added support for the
LpPool
operator - Added support for the
GreaterOrEqual
operator - Added support for dynamic inputs in
onnx_tensorrt
python backend - Added FAQ section for commonly asked questions
Fixes
- Fixed relative path imports for models with external weights #619
- Fixed importing loops operators with no loop-carried depedencies #619
- Worked around unsupported BOOL concats through casting #620
- Fixed compilation error with GCC9 #568
Removed
- Removed
onnx_tensorrt/config.py
as it is no longer needed
TensorRT 7.2.1 ONNX Parser
Open source release of TensorRT 7.2.1 ONNX Parser.
Added
- Added support for parsing large models with external data
- Added API for interfacing with TensorRT's refit feature
- Updated
onnx_tensorrt
backend to support dynamic shapes - Added support for 3D instance normalizations #515
- Improved clarity on the resize modes TRT supports #512
- Added Changelog
Changed
- Unified docker usage between ONNX-TensorRT and TensorRT.
Removed
- Removed deprecated docker files.
- Removed deprecated
setup.py
.
TensorRT 7.1 ONNX Parser
Open source release of TensorRT 7.1 ONNX Parser.
TensorRT 7.0 ONNX Parser
Open source release of TensorRT 7.0 ONNX Parser.
TensorRT 6.0 ONNX Parser
Open source release of TensorRT 6.0 ONNX Parser.