jinluyang

maybe some advices for cmake

6

1，I think in FindNCCL.cmake, the "set(NCCL_INCLUDE_DIR $ENV{NCCL_INCLUDE_DIR} CACHE ...)" should better be surounded by a "if (DEFINED ENV{...} " thing, to avoid the variable in the cache to be set...

When indices_shape is a tensor, cannot index it

2

https://github.com/onnx/onnx-tensorflow/blob/0874ca1378a8fe2d06e66f23323c3f828652e900/onnx_tf/handlers/backend/gather_and_scatter_mixin.py#L69 if tf_shape returns a tensor, indexing with indices_shape gives an error: https://github.com/onnx/onnx-tensorflow/blob/0874ca1378a8fe2d06e66f23323c3f828652e900/onnx_tf/handlers/backend/gather_and_scatter_mixin.py#L74 TypeError: slice indices must be integers or None or have an __index__ method

增加svm的参数选择、是否使用bigram、是否使用停用词。可以将只出现一两次的词归为停用词。但是在preprocess函数中去停用词使得速度大大变慢，需要改进但我不知道该怎么改。这是我用github的第一次pull request，多多指教。

I want to modify this gbdt code to get a gbdt for multi-class classification. Is it doable? thanks.

This package is excellent, but here are some problems when I use it for production: 1. sometimes when using rotatingfile ,the message (of probably some of the processes) keep being...

Hello, great job. In the README it seems we just support CUDA backend and openVINO backend but how about TensorRT backend which is used in ONNXruntime by default on Nvidia...

on RTX4090 running llama3-8B, allocate_kv_data_batchsize=10, I encountered the error of the following: CUDA Error: misaligned address (716) /code/gemv/include/attention/prefill.cuh: line 1918 at function cudaLaunchKernel((void*)kernel, nblks, nthrs, args, smem_size, stream) terminate called...