-
### Actual behavior
```
Build the libraries..
python3 prepare_test_libs.py
/usr/local/lib/python3.8/dist-packages/tvm/target/target.py:799: UserWarning: tvm.target.create() is being deprecated. …
-
TVM loads onnx model with `split` operator leads to a crash when loading it to TVM using the following script. It threw "indices_or_sections need to be able to divide input.shape[axis]"
```
impo…
-
DLR Build Machine (and target machine both) is NVidia Jetson Xavier AGX.
Ubuntu 18.04 JetPack4.6
## Software Info:
```
xavier:~$ jetson_release
- NVIDIA Jetson AGX Xavier [16GB]
* Jetpack 4…
-
【重要】[中文文档](https://tvm.hyper.ai/docs)是基于 tvm 0.10.0，对齐[英文文档 0.12 stable 版本](https://github.com/apache/tvm/tree/v0.12.0/docs)，非 v0.13 dev 版本！！！
**本任务包含以下文档：**
* - [ ] [章节概览](https://tvm.apache.or…
-
For the LSTM below, when `batch_size != 1` (i.e., the size of first dimension input), compiling will lead to an unexpected crash and throw `Check failed: *axis_ptr == 1 (2 vs. 1) : cannot squeeze axis…
-
Hi there, executing the following code causes a crash:
```
from tvm.meta_schedule.testing.relay_workload import get_network
get_network('bert_base', [1, 128])
```
```
(py38) root@d243fdd3cf8…
-
Hi,
I'm starting this thread to collect issues that are likely caused by various overhead in MXNet execution so that we can focus the efforts in solving them. The focus is everything other than the…
-
The reason for this problem is the second input --indices cannot a dynamic shape tensor.
self._construct_nodes(graph)
File "/home/workspace/tvm/python/frontend/onnx.py", line 6567, in _c…
-
### Install from Source
The page at https://tvm.apache.org/docs/install/from_source.html says this about LLVM:
> We highly recommend to build with LLVM to enable all the features.
### Additions…
jchia updated
7 months ago
-
I was working on adding support for the TFLite op `Batch_MatMul`. When looking at the tests, I was a bit puzzled as to why there was already a test for that operator and why it is passing.
https://…