TensorRT

TensorRT copied to clipboard

feat: support aten._local_scalar_dense converter

3

# Description A converter for the torch.ops.aten._local_scalar_dense operation, a low-level operation in PyTorch used internally to extract a scalar value from a tensor containing a single element. To reviewer, I...

chohk88

## Bug Description All previous lines work as expected, but cell number 28 in this example notebook: https://github.com/pytorch/TensorRT/blob/main/notebooks/qat-ptq-workflow.ipynb yields this error: ``` W0425 19:29:52.724189 140194752341824 _compile.py:108] Input graph is a...

choosehappy

## Bug Description Using main branch, BERT torchscript test fails FAILED models/test_models.py::TestModels::test_bert_base_uncased - RuntimeError: Schema not found for node. File a bug report. Node: %6932 : int = aten::add(%5840, %6931,...

peri044

## ❓ Question I am attempting to execute [PTQ](https://pytorch.org/TensorRT/user_guide/ptq.html). During the compiling process, I get the following exception: ``` DEBUG: [Torch-TensorRT TorchScript Conversion Context] - Finalize: %142 : Tensor =...

srdecny

Aten scatter converter

1

Dependency of PR- #2519

apbose

🐛 [Bug] Exporting `OptimizedModule` compiled model

6

## Bug Description Hi All, How are you? I'm trying to save complied module but encountering errors. After I compiled my model I noticed that its type is `OptimizedModule`. Following...

AvivSham

# Description Fix a bug when the module outputs are non-tensors (example: torch.ops.aten.sym_size will return integers) ## Type of change Please delete options that are not relevant and/or add your...

peri044

feat: add a pre-AOT lowering pass to remove detach ops

6

# Description Added a pre-AOT lowering pass to remove `detach` ops Fixes #2657 ## Type of change - New feature (non-breaking change which adds functionality) # Checklist: - [x] My...

zewenli98

❓ [Question] Output shape error in deconvolution layer when model is quantized with pytorch-quantization and using torch-tensorrt via torchscript

3

## ❓ Question While using a simple model with int8 quantization (pytorch-quantization) when the output layer is deconvolution, torchscript to torch-tensorrt conversion fails with wrong number of output channels. If...

oazeybekoglu

feat: Implement FP8 functionality

4

# Description This PR adds FP8 & BF16 datatype support. It also implements converter for FP8 quantized ops. ## Type of change Please delete options that are not relevant and/or...

peri044