Torch-TensorRT v1.1.1

[narendasan]

Torch-TensorRT v1.1.1

Adding support for Torch-TensorRT on Jetpack 5.0 Developer Preview

Torch-TensorRT 1.1.1 is a patch release for Torch-TensorRT 1.1 that targets PyTorch 1.11, CUDA 11.4/11.3, TensorRT 8.4 EA/8.2 and cuDNN 8.3/8.2 intended to add support for Torch-TensorRT on Jetson / Jetpack 5.0 DP. As this release is primarily targeted at adding support for Jetpack 5.0DP for the 1.1 feature set we will not be distributing pre-compiled binaries for this release so as not to break compatibility with the current stack for existing users who install directly from GitHub. Please follow the instructions for installation on Jetson in the documentation to install this release: https://pytorch.org/TensorRT/tutorials/installation.html#compiling-from-source

Known Limitations

• We have observed in testing, higher than normal numerical instability on Jetpack 5.0 DP. These issues are not observed on x86_64 based platforms. This numerical instability has not been found to decrease model accuracy in our test suite.

What's Changed

• feat: Upgrade TensorRT to 8.4 EA by @peri044 in feat: Upgrade TensorRT to 8.4 EA #1158

Full Changelog: v1.1.0...v1.1.1

Operators Supported

Operators Currently Supported Through Converters

• aten::_convolution(Tensor input, Tensor weight, Tensor? bias, int[] stride, int[] padding, int[] dilation, bool transposed, int[] output_padding, int groups, bool benchmark, bool deterministic, bool cudnn_enabled, bool allow_tf32) -> (Tensor)
• aten::_convolution.deprecated(Tensor input, Tensor weight, Tensor? bias, int[] stride, int[] padding, int[] dilation, bool transposed, int[] output_padding, int groups, bool benchmark, bool deterministic, bool cudnn_enabled) -> (Tensor)
• aten::abs(Tensor self) -> (Tensor)
• aten::acos(Tensor self) -> (Tensor)
• aten::acosh(Tensor self) -> (Tensor)
• aten::adaptive_avg_pool1d(Tensor self, int[1] output_size) -> (Tensor)
• aten::adaptive_avg_pool2d(Tensor self, int[2] output_size) -> (Tensor)
• aten::adaptive_avg_pool3d(Tensor self, int[3] output_size) -> (Tensor)
• aten::adaptive_max_pool1d(Tensor self, int[2] output_size) -> (Tensor, Tensor)
• aten::adaptive_max_pool2d(Tensor self, int[2] output_size) -> (Tensor, Tensor)
• aten::adaptive_max_pool3d(Tensor self, int[3] output_size) -> (Tensor, Tensor)
• aten::add.Scalar(Tensor self, Scalar other, Scalar alpha=1) -> (Tensor)
• aten::add.Tensor(Tensor self, Tensor other, Scalar alpha=1) -> (Tensor)
• aten::add_.Tensor(Tensor(a!) self, Tensor other, *, Scalar alpha=1) -> (Tensor(a!))
• aten::asin(Tensor self) -> (Tensor)
• aten::asinh(Tensor self) -> (Tensor)
• aten::atan(Tensor self) -> (Tensor)
• aten::atanh(Tensor self) -> (Tensor)
• aten::avg_pool1d(Tensor self, int[1] kernel_size, int[1] stride=[], int[1] padding=[0], bool ceil_mode=False, bool count_include_pad=True) -> (Tensor)
• aten::avg_pool2d(Tensor self, int[2] kernel_size, int[2] stride=[], int[2] padding=[0, 0], bool ceil_mode=False, bool count_include_pad=True, int? divisor_override=None) -> (Tensor)
• aten::avg_pool3d(Tensor self, int[3] kernel_size, int[3] stride=[], int[3] padding=[], bool ceil_mode=False, bool count_include_pad=True, int? divisor_override=None) -> (Tensor)
• aten::batch_norm(Tensor input, Tensor? gamma, Tensor? beta, Tensor? mean, Tensor? var, bool training, float momentum, float eps, bool cudnn_enabled) -> (Tensor)
• aten::bmm(Tensor self, Tensor mat2) -> (Tensor)
• aten::cat(Tensor[] tensors, int dim=0) -> (Tensor)
• aten::ceil(Tensor self) -> (Tensor)
• aten::clamp(Tensor self, Scalar? min=None, Scalar? max=None) -> (Tensor)
• aten::clamp_max(Tensor self, Scalar max) -> (Tensor)
• aten::clamp_min(Tensor self, Scalar min) -> (Tensor)
• aten::constant_pad_nd(Tensor self, int[] pad, Scalar value=0) -> (Tensor)
• aten::cos(Tensor self) -> (Tensor)
• aten::cosh(Tensor self) -> (Tensor)
• aten::cumsum(Tensor self, int dim, *, int? dtype=None) -> (Tensor)
• aten::div.Scalar(Tensor self, Scalar other) -> (Tensor)
• aten::div.Tensor(Tensor self, Tensor other) -> (Tensor)
• aten::div.Tensor_mode(Tensor self, Tensor other, *, str? rounding_mode) -> (Tensor)
• aten::div_.Scalar(Tensor(a!) self, Scalar other) -> (Tensor(a!))
• aten::div_.Tensor(Tensor(a!) self, Tensor other) -> (Tensor(a!))
• aten::elu(Tensor self, Scalar alpha=1, Scalar scale=1, Scalar input_scale=1) -> (Tensor)
• aten::embedding(Tensor weight, Tensor indices, int padding_idx=-1, bool scale_grad_by_freq=False, bool sparse=False) -> (Tensor)
• aten::eq.Scalar(Tensor self, Scalar other) -> (Tensor)
• aten::eq.Tensor(Tensor self, Tensor other) -> (Tensor)
• aten::erf(Tensor self) -> (Tensor)
• aten::exp(Tensor self) -> (Tensor)
• aten::expand(Tensor(a) self, int[] size, *, bool implicit=False) -> (Tensor(a))
• aten::expand_as(Tensor(a) self, Tensor other) -> (Tensor(a))
• aten::fake_quantize_per_channel_affine(Tensor self, Tensor scale, Tensor zero_point, int axis, int quant_min, int quant_max) -> (Tensor)
• aten::fake_quantize_per_tensor_affine(Tensor self, float scale, int zero_point, int quant_min, int quant_max) -> (Tensor)
• aten::flatten.using_ints(Tensor self, int start_dim=0, int end_dim=-1) -> (Tensor)
• aten::floor(Tensor self) -> (Tensor)
• aten::floor_divide(Tensor self, Tensor other) -> (Tensor)
• aten::floor_divide.Scalar(Tensor self, Scalar other) -> (Tensor)
• aten::ge.Scalar(Tensor self, Scalar other) -> (Tensor)
• aten::ge.Tensor(Tensor self, Tensor other) -> (Tensor)
• aten::gru_cell(Tensor input, Tensor hx, Tensor w_ih, Tensor w_hh, Tensor? b_ih=None, Tensor? b_hh=None) -> (Tensor)
• aten::gt.Scalar(Tensor self, Scalar other) -> (Tensor)
• aten::gt.Tensor(Tensor self, Tensor other) -> (Tensor)
• aten::hardtanh(Tensor self, Scalar min_val=-1, Scalar max_val=1) -> (Tensor)
• aten::hardtanh_(Tensor(a!) self, Scalar min_val=-1, Scalar max_val=1) -> (Tensor(a!))
• aten::index.Tensor(Tensor self, Tensor?[] indices) -> (Tensor)
• aten::instance_norm(Tensor input, Tensor? weight, Tensor? bias, Tensor? running_mean, Tensor? running_var, bool use_input_stats, float momentum, float eps, bool cudnn_enabled) -> (Tensor)
• aten::layer_norm(Tensor input, int[] normalized_shape, Tensor? gamma, Tensor? beta, float eps, bool cudnn_enabled) -> (Tensor)
• aten::le.Scalar(Tensor self, Scalar other) -> (Tensor)
• aten::le.Tensor(Tensor self, Tensor other) -> (Tensor)
• aten::leaky_relu(Tensor self, Scalar negative_slope=0.01) -> (Tensor)
• aten::leaky_relu_(Tensor(a!) self, Scalar negative_slope=0.01) -> (Tensor(a!))
• aten::linear(Tensor input, Tensor weight, Tensor? bias=None) -> (Tensor)
• aten::log(Tensor self) -> (Tensor)
• aten::lstm_cell(Tensor input, Tensor[] hx, Tensor w_ih, Tensor w_hh, Tensor? b_ih=None, Tensor? b_hh=None) -> (Tensor, Tensor)
• aten::lt.Scalar(Tensor self, Scalar other) -> (Tensor)
• aten::lt.Tensor(Tensor self, Tensor other) -> (Tensor)
• aten::masked_fill.Scalar(Tensor self, Tensor mask, Scalar value) -> (Tensor)
• aten::matmul(Tensor self, Tensor other) -> (Tensor)
• aten::max(Tensor self) -> (Tensor)
• aten::max.dim(Tensor self, int dim, bool keepdim=False) -> (Tensor values, Tensor indices)
• aten::max.other(Tensor self, Tensor other) -> (Tensor)
• aten::max_pool1d(Tensor self, int[1] kernel_size, int[1] stride=[], int[1] padding=[], int[1] dilation=[], bool ceil_mode=False) -> (Tensor)
• aten::max_pool2d(Tensor self, int[2] kernel_size, int[2] stride=[], int[2] padding=[0, 0], int[2] dilation=[1, 1], bool ceil_mode=False) -> (Tensor)
• aten::max_pool3d(Tensor self, int[3] kernel_size, int[3] stride=[], int[3] padding=[], int[3] dilation=[], bool ceil_mode=False) -> (Tensor)
• aten::mean(Tensor self, *, int? dtype=None) -> (Tensor)
• aten::mean.dim(Tensor self, int[] dim, bool keepdim=False, *, int? dtype=None) -> (Tensor)
• aten::min(Tensor self) -> (Tensor)
• aten::min.other(Tensor self, Tensor other) -> (Tensor)
• aten::mul.Scalar(Tensor self, Scalar other) -> (Tensor)
• aten::mul.Tensor(Tensor self, Tensor other) -> (Tensor)
• aten::mul_.Tensor(Tensor(a!) self, Tensor other) -> (Tensor(a!))
• aten::narrow(Tensor(a) self, int dim, int start, int length) -> (Tensor(a))
• aten::narrow.Tensor(Tensor(a) self, int dim, Tensor start, int length) -> (Tensor(a))
• aten::ne.Scalar(Tensor self, Scalar other) -> (Tensor)
• aten::ne.Tensor(Tensor self, Tensor other) -> (Tensor)
• aten::neg(Tensor self) -> (Tensor)
• aten::norm.ScalarOpt_dim(Tensor self, Scalar? p, int[1] dim, bool keepdim=False) -> (Tensor)
• aten::permute(Tensor(a) self, int[] dims) -> (Tensor(a))
• aten::pixel_shuffle(Tensor self, int upscale_factor) -> (Tensor)
• aten::pow.Tensor_Scalar(Tensor self, Scalar exponent) -> (Tensor)
• aten::pow.Tensor_Tensor(Tensor self, Tensor exponent) -> (Tensor)
• aten::prelu(Tensor self, Tensor weight) -> (Tensor)
• aten::prod(Tensor self, *, int? dtype=None) -> (Tensor)
• aten::prod.dim_int(Tensor self, int dim, bool keepdim=False, *, int? dtype=None) -> (Tensor)
• aten::reciprocal(Tensor self) -> (Tensor)
• aten::reflection_pad1d(Tensor self, int[2] padding) -> (Tensor)
• aten::reflection_pad2d(Tensor self, int[4] padding) -> (Tensor)
• aten::relu(Tensor input) -> (Tensor)
• aten::relu_(Tensor(a!) self) -> (Tensor(a!))
• aten::repeat(Tensor self, int[] repeats) -> (Tensor)
• aten::replication_pad1d(Tensor self, int[2] padding) -> (Tensor)
• aten::replication_pad2d(Tensor self, int[4] padding) -> (Tensor)
• aten::replication_pad3d(Tensor self, int[6] padding) -> (Tensor)
• aten::reshape(Tensor self, int[] shape) -> (Tensor)
• aten::roll(Tensor self, int[1] shifts, int[1] dims=[]) -> (Tensor)
• aten::rsub.Scalar(Tensor self, Scalar other, Scalar alpha=1) -> (Tensor)
• aten::rsub.Tensor(Tensor self, Tensor other, Scalar alpha=1) -> (Tensor)
• aten::select.int(Tensor(a) self, int dim, int index) -> (Tensor(a))
• aten::sigmoid(Tensor input) -> (Tensor)
• aten::sigmoid_(Tensor(a!) self) -> (Tensor(a!))
• aten::sin(Tensor self) -> (Tensor)
• aten::sinh(Tensor self) -> (Tensor)
• aten::slice.Tensor(Tensor(a) self, int dim=0, int? start=None, int? end=None, int step=1) -> (Tensor(a))
• aten::softmax.int(Tensor self, int dim, int? dtype=None) -> (Tensor)
• aten::split(Tensor self, int[] split_sizes, int dim=0) -> (Tensor[])
• aten::split.Tensor(Tensor(a) self, int split_size, int dim=0) -> (Tensor[])
• aten::split_with_sizes(Tensor(a) self, int[] split_sizes, int dim=0) -> (Tensor[])
• aten::sqrt(Tensor self) -> (Tensor)
• aten::squeeze.dim(Tensor(a) self, int dim) -> (Tensor(a))
• aten::stack(Tensor[] tensors, int dim=0) -> (Tensor)
• aten::sub.Scalar(Tensor self, Scalar other, Scalar alpha=1) -> (Tensor)
• aten::sub.Tensor(Tensor self, Tensor other, Scalar alpha=1) -> (Tensor)
• aten::sub_.Tensor(Tensor(a!) self, Tensor other, *, Scalar alpha=1) -> (Tensor(a!))
• aten::sum(Tensor self, *, int? dtype=None) -> (Tensor)
• aten::sum.dim_IntList(Tensor self, int[1] dim, bool keepdim=False, *, int? dtype=None) -> (Tensor)
• aten::t(Tensor self) -> (Tensor)
• aten::tan(Tensor self) -> (Tensor)
• aten::tanh(Tensor input) -> (Tensor)
• aten::tanh_(Tensor(a!) self) -> (Tensor(a!))
• aten::to.device(Tensor(a) self, Device device, int dtype, bool non_blocking=False, bool copy=False, int? memory_format=None) -> (Tensor(a))
• aten::to.dtype(Tensor self, int dtype, bool non_blocking=False, bool copy=False, int? memory_format=None) -> (Tensor)
• aten::to.other(Tensor self, Tensor other, bool non_blocking=False, bool copy=False, int? memory_format=None) -> (Tensor)
• aten::to.prim_Device(Tensor(a) self, Device? device, int? dtype=None, bool non_blocking=False, bool copy=False) -> (Tensor(a|b))
• aten::topk(Tensor self, int k, int dim=-1, bool largest=True, bool sorted=True) -> (Tensor values, Tensor indices)
• aten::transpose.int(Tensor(a) self, int dim0, int dim1) -> (Tensor(a))
• aten::unbind.int(Tensor(a -> *) self, int dim=0) -> (Tensor[])
• aten::unsqueeze(Tensor(a) self, int dim) -> (Tensor(a))
• aten::upsample_bilinear2d(Tensor self, int[2] output_size, bool align_corners, float? scales_h=None, float? scales_w=None) -> (Tensor)
• aten::upsample_bilinear2d.vec(Tensor input, int[]? output_size, bool align_corners, float[]? scale_factors) -> (Tensor)
• aten::upsample_linear1d(Tensor self, int[1] output_size, bool align_corners, float? scales=None) -> (Tensor)
• aten::upsample_linear1d.vec(Tensor input, int[]? output_size, bool align_corners, float[]? scale_factors) -> (Tensor)
• aten::upsample_nearest1d(Tensor self, int[1] output_size, float? scales=None) -> (Tensor)
• aten::upsample_nearest1d.vec(Tensor input, int[]? output_size, float[]? scale_factors) -> (Tensor)
• aten::upsample_nearest2d(Tensor self, int[2] output_size, float? scales_h=None, float? scales_w=None) -> (Tensor)
• aten::upsample_nearest2d.vec(Tensor input, int[]? output_size, float[]? scale_factors) -> (Tensor)
• aten::upsample_nearest3d(Tensor self, int[3] output_size, float? scales_d=None, float? scales_h=None, float? scales_w=None) -> (Tensor)
• aten::upsample_nearest3d.vec(Tensor input, int[]? output_size, float[]? scale_factors) -> (Tensor)
• aten::upsample_trilinear3d(Tensor self, int[3] output_size, bool align_corners, float? scales_d=None, float? scales_h=None, float? scales_w=None) -> (Tensor)
• aten::upsample_trilinear3d.vec(Tensor input, int[]? output_size, bool align_corners, float[]? scale_factors) -> (Tensor)
• aten::view(Tensor(a) self, int[] size) -> (Tensor(a))
• trt::const(Tensor self) -> (Tensor)

Operators Currently Supported Through Evaluators

• aten::Bool.float(float b) -> (bool)
• aten::Bool.int(int a) -> (bool)
• aten::Float.Scalar(Scalar a) -> float
• aten::Float.bool(bool a) -> float
• aten::Float.int(int a) -> float
• aten::Int.Scalar(Scalar a) -> int
• aten::Int.bool(bool a) -> int
• aten::Int.float(float a) -> int
• aten::Int.int(int a) -> int
• aten::and(int a, int b) -> (bool)
• aten::and.bool(bool a, bool b) -> (bool)
• aten::getitem.t(t list, int idx) -> (t(*))
• aten::is(t1 self, t2 obj) -> bool
• aten::isnot(t1 self, t2 obj) -> bool
• aten::not(bool self) -> bool
• aten::or(int a, int b) -> (bool)
• aten::__range_length(int lo, int hi, int step) -> int
• aten::__round_to_zero_floordiv(int a, int b) -> (int)
• aten::xor(int a, int b) -> (bool)
• aten::add.float(float a, float b) -> (float)
• aten::add.int(int a, int b) -> (int)
• aten::add.str(str a, str b) -> (str)
• aten::add_.t(t self, t[] b) -> (t[])
• aten::append.t(t self, t(c -> *) el) -> (t)
• aten::arange(Scalar end, *, int? dtype=None, int? layout=None,
  Device? device=None, bool? pin_memory=None) -> (Tensor)
• aten::arange.start(Scalar start, Scalar end, *, ScalarType? dtype=None,
  Layout? layout=None, Device? device=None, bool? pin_memory=None) -> (Tensor)
• aten::arange.start_step(Scalar start, Scalar end, Scalar step, *, ScalarType? dtype=None,
  Layout? layout=None, Device? device=None, bool? pin_memory=None) -> (Tensor)
• aten::clone(Tensor self, *, int? memory_format=None) -> (Tensor)
• aten::copy_(Tensor(a!) self, Tensor src, bool non_blocking=False) -> (Tensor(a!))
• aten::dim(Tensor self) -> int
• aten::div.float(float a, float b) -> (float)
• aten::div.int(int a, int b) -> (float)
• aten::eq.bool(bool a, bool b) -> (bool)
• aten::eq.float(float a, float b) -> (bool)
• aten::eq.float_int(float a, int b) -> (bool)
• aten::eq.int(int a, int b) -> (bool)
• aten::eq.int_float(int a, float b) -> (bool)
• aten::eq.str(str a, str b) -> (bool)
• aten::extend.t(t self, t[] other) -> ()
• aten::floor.float(float a) -> (int)
• aten::floor.int(int a) -> (int)
• aten::floordiv.float(float a, float b) -> (int)
• aten::floordiv.int(int a, int b) -> (int)
• aten::format(str self, ...) -> (str)
• aten::ge.bool(bool a, bool b) -> (bool)
• aten::ge.float(float a, float b) -> (bool)
• aten::ge.float_int(float a, int b) -> (bool)
• aten::ge.int(int a, int b) -> (bool)
• aten::ge.int_float(int a, float b) -> (bool)
• aten::gt.bool(bool a, bool b) -> (bool)
• aten::gt.float(float a, float b) -> (bool)
• aten::gt.float_int(float a, int b) -> (bool)
• aten::gt.int(int a, int b) -> (bool)
• aten::gt.int_float(int a, float b) -> (bool)
• aten::is_floating_point(Tensor self) -> (bool)
• aten::le.bool(bool a, bool b) -> (bool)
• aten::le.float(float a, float b) -> (bool)
• aten::le.float_int(float a, int b) -> (bool)
• aten::le.int(int a, int b) -> (bool)
• aten::le.int_float(int a, float b) -> (bool)
• aten::len.t(t[] a) -> (int)
• aten::lt.bool(bool a, bool b) -> (bool)
• aten::lt.float(float a, float b) -> (bool)
• aten::lt.float_int(float a, int b) -> (bool)
• aten::lt.int(int a, int b) -> (bool)
• aten::lt.int_float(int a, float b) -> (bool)
• aten::mul.float(float a, float b) -> (float)
• aten::mul.int(int a, int b) -> (int)
• aten::ne.bool(bool a, bool b) -> (bool)
• aten::ne.float(float a, float b) -> (bool)
• aten::ne.float_int(float a, int b) -> (bool)
• aten::ne.int(int a, int b) -> (bool)
• aten::ne.int_float(int a, float b) -> (bool)
• aten::neg.int(int a) -> (int)
• aten::numel(Tensor self) -> int
• aten::pow.float(float a, float b) -> (float)
• aten::pow.float_int(float a, int b) -> (float)
• aten::pow.int(int a, int b) -> (float)
• aten::pow.int_float(int a, float b) -> (float)
• aten::size(Tensor self) -> (int[])
• aten::size.int(Tensor self, int dim) -> (int)
• aten::slice.t(t[] l, int start, int end=9223372036854775807, int step=1) -> (t[])
• aten::sqrt.float(float a) -> (float)
• aten::sqrt.int(int a) -> (float)
• aten::sub.float(float a, float b) -> (float)
• aten::sub.int(int a, int b) -> (int)
• aten::tensor(t[] data, *, int? dtype=None, Device? device=None, bool requires_grad=False) -> (Tensor)
• prim::dtype(Tensor a) -> (int)
• prim::max.bool(bool a, bool b) -> (bool)
• prim::max.float(float a, float b) -> (bool)
• prim::max.float_int(float a, int b) -> (bool)
• prim::max.int(int a, int b) -> (bool)
• prim::max.int_float(int a, float b) -> (bool)
• prim::max.self_int(int[] self) -> (int)
• prim::min.bool(bool a, bool b) -> (bool)
• prim::min.float(float a, float b) -> (bool)
• prim::min.float_int(float a, int b) -> (bool)
• prim::min.int(int a, int b) -> (bool)
• prim::min.int_float(int a, float b) -> (bool)
• prim::min.self_int(int[] self) -> (int)
• prim::shape(Tensor a) -> (int[])

---

This discussion was created from the release Torch-TensorRT v1.1.1.