pytorch / pytorch/TensorRT

error in data types

Open
#3,614 4 comments 0 reactions 1 assignee View on GitHub

@lanluo-nvidia is already working on this.

Since Jul 19, 2025.

story: Operator Coverage & Converters
Dominant language
Python
Stars
3k
Forks
410
Avg merge
3d 18h
Merged PRs (30d)
78

Description

i have got those errors during build from scratch using cmake

~/projects/m.tarek_master/packages/TensorRT/build$ make -j20
[ 1%] Built target core_util_logging
[ 2%] Building CXX object core/util/CMakeFiles/core_util.dir/trt_util.cpp.o
In file included from /home/cplus/projects/m.tarek_master/packages/TensorRT/core/util/trt_util.cpp:1:
/home/cplus/projects/m.tarek_master/packages/TensorRT/core/util/trt_util.h: In function ‘std::ostream& nvinfer1::operator<<(std::ostream&, const nvinfer1::DataType&)’:
/home/cplus/projects/m.tarek_master/packages/TensorRT/core/util/trt_util.h:56:30: error: ‘kINT64’ is not a member of ‘nvinfer1::DataType’; did you mean ‘kINT8’?
56 | case nvinfer1::DataType::kINT64:
| ^~~~~~
| kINT8
/home/cplus/projects/m.tarek_master/packages/TensorRT/core/util/trt_util.h:58:30: error: ‘kBF16’ is not a member of ‘nvinfer1::DataType’
58 | case nvinfer1::DataType::kBF16:
| ^~~~~
/home/cplus/projects/m.tarek_master/packages/TensorRT/core/util/trt_util.cpp: In function ‘const std::unordered_map<c10::ScalarType, nvinfer1::DataType>& torch_tensorrt::core::util::{anonymous}::get_at_trt_type_map()’:
/home/cplus/projects/m.tarek_master/packages/TensorRT/core/util/trt_util.cpp:295:39: error: ‘kINT64’ is not a member of ‘nvinfer1::DataType’; did you mean ‘kINT8’?
295 | {at::kLong, nvinfer1::DataType::kINT64},
| ^~~~~~
| kINT8
/home/cplus/projects/m.tarek_master/packages/TensorRT/core/util/trt_util.cpp:299:43: error: ‘kBF16’ is not a member of ‘nvinfer1::DataType’
299 | {at::kBFloat16, nvinfer1::DataType::kBF16}};
| ^~~~~
/home/cplus/projects/m.tarek_master/packages/TensorRT/core/util/trt_util.cpp:299:49: error: could not convert ‘{{c10::kFloat, nvinfer1::DataType::kFLOAT}, {c10::kHalf, nvinfer1::DataType::kHALF}, {c10::kInt, nvinfer1::DataType::kINT32}, {c10::kLong, }, {c10::kChar, nvinfer1::DataType::kINT8}, {c10::kByte, nvinfer1::DataType::kINT8}, {c10::kBool, nvinfer1::DataType::kBOOL}, {c10::kBFloat16, }}’ from ‘’ to ‘const std::unordered_map<c10::ScalarType, nvinfer1::DataType>’
299 | {at::kBFloat16, nvinfer1::DataType::kBF16}};
| ^
| |
|
/home/cplus/projects/m.tarek_master/packages/TensorRT/core/util/trt_util.cpp: In function ‘const std::unordered_map<nvinfer1::DataType, c10::ScalarType>& torch_tensorrt::core::util::{anonymous}::get_trt_at_type_map()’:
/home/cplus/projects/m.tarek_master/packages/TensorRT/core/util/trt_util.cpp:308:28: error: ‘kINT64’ is not a member of ‘nvinfer1::DataType’; did you mean ‘kINT8’?
308 | {nvinfer1::DataType::kINT64, at::kLong},
| ^~~~~~
| kINT8
/home/cplus/projects/m.tarek_master/packages/TensorRT/core/util/trt_util.cpp:311:28: error: ‘kBF16’ is not a member of ‘nvinfer1::DataType’
311 | {nvinfer1::DataType::kBF16, at::kBFloat16}};
| ^~~~~
/home/cplus/projects/m.tarek_master/packages/TensorRT/core/util/trt_util.cpp:311:49: error: could not convert ‘{{nvinfer1::DataType::kFLOAT, c10::kFloat}, {nvinfer1::DataType::kHALF, c10::kHalf}, {nvinfer1::DataType::kINT32, c10::kInt}, {, c10::kLong}, {nvinfer1::DataType::kINT8, c10::kChar}, {nvinfer1::DataType::kBOOL, c10::kBool}, {, c10::kBFloat16}}’ from ‘’ to ‘const std::unordered_map<nvinfer1::DataType, c10::ScalarType>’
311 | {nvinfer1::DataType::kBF16, at::kBFloat16}};
| ^
| |
|
make[2]: *** [core/util/CMakeFiles/core_util.dir/build.make:93: core/util/CMakeFiles/core_util.dir/trt_util.cpp.o] Error 1
make[1]: *** [CMakeFiles/Makefile2:603: co

i use cuda 11.8 with tensorrt 10.12.0.36

Contributor guide

Open the contributing guide

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Assessment

This issue has not been assessed yet.

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.