-
After watching chaomix's video, I decided to go ahead and put these decomps on my steam deck. All of a sudden, the game audio has completely disappeared. tested on both modded sonic 1 and vanilla soni…
-
### 🐛 Describe the bug
For lowering graphs using compile_fx_inner, we are hitting a cyclical error re: decompositions for 20 operators. These operators are all present in the torch decomp table, but …
-
### 🐛 Describe the bug
```
import torch
from torch.nn import *
class Repro(torch.nn.Module):
def __init__(self):
super().__init__()
def forward(self):
arange_1 = to…
-
Repro:
```
import torch
import torchdynamo
import torchinductor
from torchinductor import config
torchinductor.config.debug = True
def relu(x0):
return torch.nn.functional.relu(x0)
…
-
The build system currently runs compile jobs in parallel to decrease compile time.
This achieved using the [multiprocessing](https://docs.python.org/3/library/multiprocessing.html) library. The multi…
-
https://hud.pytorch.org/hud/pytorch/pytorch/master/1?per_page=50&name_filter=inductor
-
See pytorch/pytorch#93757 for list of missing ops.
I've seen this op recently show up in `pytorch_CycleGAN_and_pix2pix` and `pytorch_stargan` when using the latest pytorch. Args are:
```
[WARNIN…
-
-
@jansel pointed out some of the existing scattering ops decompose into mutable variants, like in [this example](https://github.com/pytorch/torchdynamo/blob/b20f7184207e1a4dd5a0ab736d3d2854a44081a1/tor…
-
It would be nice to have more testing infra around "performance of optimizations".
One idea would be to measure memory reads/writes between different kernels, and verifying that those are some valu…