# \[RFC\] tlcpack: Thirdparty Binary Packages

**URL:** <https://discuss.tvm.apache.org/t/rfc-tlcpack-thirdparty-binary-packages/7903>\
**Category:** RFC\
**Created:** [September 15, 2020, 5:36am UTC](https://discuss.tvm.apache.org/t/rfc-tlcpack-thirdparty-binary-packages/7903 "2020-09-15T05:36:37Z")\
**Posts on this page:** 1\
**Showing post:** 9

<div class="post-metadata">

**Author:** ![hsuan](https://discuss.tvm.apache.org/letter_avatar_proxy/v4/letter/h/ccd318/32.png) [@hsuan](https://discuss.tvm.apache.org/u/hsuan)\
**Post date:** [September 26, 2020, 7:58pm UTC](https://discuss.tvm.apache.org/t/rfc-tlcpack-thirdparty-binary-packages/7903/9 "2020-09-26T19:58:59Z")

</div>

Thanks for your work.

I tested the wheels however I got CUDA error with tlcpack\_cu102-0.7.dev1-cp36-cp36m-manylinux2014\_x86\_64.whl:

```
 tvm._ffi.base.TVMError: Traceback (most recent call last):
  [bt] (3) /usr/local/lib/python3.6/dist-packages/tvm/libtvm.so(TVMFuncCall+0x48) [0x7fe7e6f0dc48]
  [bt] (2) /usr/local/lib/python3.6/dist-packages/tvm/libtvm.so(std::_Function_handler<void (tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*), tvm::runtime::detail::PackFuncVoidAddr_<4, tvm::runtime::CUDAWrappedFunc>(tvm::runtime::CUDAWrappedFunc, std::vector<tvm::runtime::detail::ArgConvertCode, std::allocator<tvm::runtime::detail::ArgConvertCode> > const&)::{lambda(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)#1}>::_M_invoke(std::_Any_data const&, tvm::runtime::TVMArgs&&, tvm::runtime::TVMRetValue*&&)+0x9e) [0x7fe7e6fae74e]
  [bt] (1) /usr/local/lib/python3.6/dist-packages/tvm/libtvm.so(tvm::runtime::CUDAWrappedFunc::operator()(tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*, void**) const+0x755) [0x7fe7e6fae645]
  [bt] (0) /usr/local/lib/python3.6/dist-packages/tvm/libtvm.so(+0x15f4505) [0x7fe7e6faa505]
  File "/workspace/tvm/src/runtime/cuda/cuda_module.cc", line 105
  File "/workspace/tvm/src/runtime/library_module.cc", line 78
CUDAError: Check failed: ret == 0 (-1 vs. 0) : cuModuleLoadData(&(module_[device_id]), data_.c_str()) failed with error: CUDA_ERROR_NOT_INITIALIZED

```

I tested this with image: `docker pull nvidia/cuda:10.2-cudnn8-devel-ubuntu18.04`

while if build tvm from source, it works without any issue…

Anyone know what could be the cause of this?

Update: I got the same error using the Dockerfile.package-cu102 provided.

The error can be produced using [https://tvm.apache.org/docs/tutorials/get\_started/relay\_quick\_start.html#sphx-glr-tutorials-get-started-relay-quick-start-py](https://tvm.apache.org/docs/tutorials/get_started/relay_quick_start.html#sphx-glr-tutorials-get-started-relay-quick-start-py)

---

_[View the full topic](https://discuss.tvm.apache.org/t/rfc-tlcpack-thirdparty-binary-packages/7903)._