tvm
tvm copied to clipboard
apache
Open deep learning compiler stack for cpu, gpu and specialized accelerators
This make use of recent work done in enabling PyTorch and ONNX tests to be run on AArch64 to actually enable the tests to run as part of CI. Co-Authored-By:...
Motivation: Currently, `StructuralEqual/Hash` take into account NDArray raw data to determine equality / compute hash. This is problematic for `link-params = True` case, because meta schedule task extraction and database...
Thanks for participating in the TVM community! We use https://discuss.tvm.ai for any general usage questions and discussions. The issue tracker is used for actionable items such as feature proposals discussion,...
add build script for csinn. cc @Mousius @areusch @driazati @gigiblender
See #12644 for context cc @Mousius @areusch @gigiblender
There are 2 meta-scheduler tests failing when we run these tests in CI on machines that have torch installed. The last change I could track that touches on that part...
### Expected behavior Thank for your great works on microTVM, I try to run MCUNet model, in [here](https://drive.google.com/file/d/1ievEPUMpA5gPdFJY3SWzB2N6kv4n9keN/view?usp=sharing) . I followed this [tutorial](https://tvm.apache.org/docs/how_to/work_with_microtvm/micro_tvmc.html#sphx-glr-how-to-work-with-microtvm-micro-tvmc-py). When I use the tutorial [model](https://github.com/tensorflow/tflite-micro/raw/main/tensorflow/lite/micro/examples/magic_wand/magic_wand.tflite), every...
On my journey in enabling Integration tests in AArch64, I stumbled upon `ctypes.tests.python.contrib.test_libtorch_ops.test_backend` (see [full error here](https://ci.tlcpack.ai/job/tvm/job/PR-11995/57/testReport/junit/ctypes.tests.python.contrib/test_libtorch_ops/Test___integration__aarch64_1_of_4___test_backend/)), which crashes running integration tests on machines with torch installed. The reason for...
When compiling [following ONNX model](https://github.com/apache/tvm/files/9526032/bug-no2.zip) with TVM, the compiler fails with errors. I think it is probably related to the Resize operation. ``` Traceback (most recent call last): File "check.py",...
Thanks for contributing to TVM! Please refer to guideline https://tvm.apache.org/docs/contribute/ for useful information and tips. After the pull request is submitted, please request code reviews from [Reviewers](https://github.com/apache/incubator-tvm/blob/master/CONTRIBUTORS.md#reviewers) by @ them...
