-
We are having ongoing efforts about supporting sparse attention in GluonNLP: https://github.com/dmlc/gluon-nlp/pull/1395. To better accelerate related kernels, we can compare the performance of these …
-
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…
-
Looks like the URL used here is outdated
https://github.com/conda-forge/libtvm-feedstock/blob/a4c7fd2fc8cfdb433c66f20c9cab103679431f54/recipe/meta.yaml#L10
https://github.com/conda-forge/libtvm-…
-
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…
-
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 d…
-
### Expected behavior
When adding an extra torch.Tensor.transpose node as output to this graph:
New:
The outputs of torch.argmax is expected to be the same for the same input in this 2 grap…
Azyka updated
7 months ago
-
I used the latest TVM to compile my model for x86_64 and for cuda_x86_64 targets (Cuda 10.2 sm_70).
After that I tried to use `model_peeker` to check the model folders
model_peeker works fine for …
-
### Expected behavior
When running Cargo check on the Rust API code, it should pass.
### Actual behavior
It fails with the following:
```
Compiling tvm-sys v0.1.1-alpha (/home/ubuntu/ch…
-
Currently pointing at mwillsey's fork, but now that his PR is merged, we can switch.
Should pick a specific revision from TVM, not just point at master!
-
## C++
+ adder.cc
```cpp
#include "adder.h"
int add(int a, int b)
{
return a + b;
}
```
+ adder.h
```cpp
extern "C" {
int add(int a, int b);
}
```
### compile command
```bash
$ g+…