LiYu Lu

close the popen stream

2

l think we should close the popen stream before function exits

Fix spelling error in function GetMaxTokenLength()

1

Fixed `GetMaxTokenLenght` spelling error

Compare with seastar ?

2

Is there a comparison test with [seastar](https://github.com/scylladb/seastar) ?

Fix device thread `gemm.h` constructor

1

Traversing the length of array B_tile is incorrect.

Some questions about data accuracy ？

1

https://github.com/leimao/CUDA-GEMM-Optimization/blob/main/include/profile_utils.cuh#L238 Why is it better to use int here? https://github.com/leimao/CUDA-GEMM-Optimization/blob/main/src/profile_cuda_gemm_fp16.cu#L14 Why is the accuracy used here so low? I see that the accuracy in apex and torch.test is relatively high....

https://github.com/NVIDIA/cutlass/issues/1879

An error occurred when I printed a tensor of type half using the program below. ```c++ #include using namespace cute; void test_subbyte_ref() { auto x = make_tensor(Int{}); // Shift tensor...

https://github.com/NVIDIA/cutlass/discussions/1867