tvm
tvm copied to clipboard
apache
Open deep learning compiler stack for cpu, gpu and specialized accelerators
Bumps [tornado](https://github.com/tornadoweb/tornado) from 6.3.3 to 6.4.1. Changelog Sourced from tornado's changelog. Release notes .. toctree:: :maxdepth: 2 releases/v6.4.1 releases/v6.4.0 releases/v6.3.3 releases/v6.3.2 releases/v6.3.1 releases/v6.3.0 releases/v6.2.0 releases/v6.1.0 releases/v6.0.4 releases/v6.0.3 releases/v6.0.2 releases/v6.0.1 releases/v6.0.0...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
As the title said, when I use TVM MetaSchdule and RPC to run tuning on another device, when I resize the terminal of host tuning proccess, a RPC runner process...
`nn.Conv3D` is bugged https://github.com/apache/tvm/blob/78a1f80bf24f1a1114f2ed7d17563d267bb38cc9/python/tvm/relax/frontend/nn/modules.py#L314-L325 line 325 should use `in_channels` instead of `self.in_channels` to make groups work. Otherwise `in_channels` calculated at line 317 would not be effectively used in weight parameters.
Bumps [requests](https://github.com/psf/requests) from 2.28.2 to 2.32.2. Release notes Sourced from requests's releases. v2.32.2 2.32.2 (2024-05-21) Deprecations To provide a more stable migration for custom HTTPAdapters impacted by the CVE changes...
#### Description This torch model has only two ops: `ReflectionPad3d` and `squeeze` Firstly, I try to export the ``torch model`` to ``onnx model``. Then I get the below. ...
This is a workaround for an upstream LLVM issue [0], which looks to be caused by the `CMAKE_INSTALL_LIBDIR` variable is used before definition. While there is an LLVM PR to...
### Actual behavior ``` Segmentation fault (core dumped) ``` ### Steps to reproduce ``` import tvm from tvm import relax import numpy as np from tvm.script import ir as I...
### Actual behavior ``` Traceback (most recent call last): File "/share_container/optfuzz/res/bugs/18_check.py", line 35, in mod = tvm.transform.Sequential([relax.transform.LiftTransformParams(), relax.transform.LiftTransformParams()])(mod) # crash here ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/software/tvm/python/tvm/ir/transform.py", line 238, in __call__ return _ffi_transform_api.RunPass(self,...
The `LiftTransformParams` pass produces additional functions, either named `$FOO_transform_params` when generating one transformation function per inference function, or `transform_params` when generating a single shared transformation function. Prior to this commit,...
Prior to this commit, the `CanonicalizeBindings` pass could identify and simplify a value that had been packed into a tuple, then extracted from it. (e.g. Simplifying `tup = (x,y); z...