Nan
Hi, https://github.com/alibaba/MNN/blob/344629419f710b39559e616f1af7bb7bd29617db/tools/cv/test/imgproc/structral_test.cpp#L42 > TEST(findContours, external_none) { VARP x = _Const(img.data(), {1, 11, 13, 1}, NHWC); ... } img is type of uint8_t `static std::vector img = { 0,0,0,0,0,0,0,0,0,0,0,0,0,` while x...
the following test would be failed in some cases: ```python python3 -m torch2trt.test --name=group ``` ``` TypeError: add_plugin_v2(): incompatible function arguments. The following argument types are supported: 1. (self: tensorrt.tensorrt.INetworkDefinition,...
Hi guys, Is it possible to supply a torch wrapper for ppl.nn? It will make it much easier to use ppl.nn. the wrapper can parse onnx file, and accept a...
- [x] I have searched to see if a similar issue already exists. yes **Describe the solution you'd like** I have a tasks pipeline and want to show it on...
这样便于生态迁移，更容易推广
TensorRT-LLM has better kernel optimization, better model ecosystem support, and more quantization algorithm support compared to other large model inference libraries. However, during use, it is not easy to demonstrate...
Hi, is there anyone can use simd to speedup the resize process? for example: [ref](https://github.com/uploadcare/pillow-simd). The throughout seems a little lower than opencv.
At this moment, CudaBuffer can be converted to torch.Tensor through `__cuda_array_interface__`. However, sometimes we have to use libtorch(at::Tensor/torch::Tensor). Is it possible to make a libtorch interface for nvcv::Tensor/ITensor ?
offset is needed in AllocFunc to let FreeFunc know the offset: AllocFunc [](int64_t size, int32_t align, int32_t&offset) FreeFunc [](void *ptr, int32_t offset)
There are many models use MoE, for instance: https://github.com/PKU-YuanGroup/MoE-LLaVA/blob/0549ce0e65119858399d2e4e88ddb4cd3db4c133/moellava/model/language_model/llava_stablelm_moe.py#L483 It would be great if the model can be exported to onnx with custom onnx node, and tensorrt can support such...