-
### Describe the bug
controlnet loader from_single_file was originally added via #4084
and method `ControlNet.from_single_file()` works for non-converted controlnets.
but for controlnets in saf…
-
Hello,
I had no problems working with ToonCrafter in the past, but somehow today I'm not able to run it. After about an hour of digging, I think it comes down to the version of Pytorch from one of …
-
When I used qfloat8 to quantize the unet model of Kolors-diffusers, it works well. But failed with qint4.
# use qint4/(qfloat8)
class KolorsUNet2DConditionModel(QuantizedDiffusersModel):
base…
-
How can i Solve it? i cant even do anything
i searched a lot but didn't find any solutions .
-
### 🚀 The feature, motivation and pitch
Some modules need to keep float32/float64/float16 constant Tensors (registered as buffers) unaffected by .to(dtype=float16, etc) operations. The most straight…
-
### Describe the feature request
Currently quantize_dynamic() takes an onnx in float32 format an outputs an onnx in int8 format.
It would be nice so that this also worked on an onnx in float16 f…
-
Just FYI, in GCC we've added support for from_chars for the C++23 std::{,b}float16_t support in https://gcc.gnu.org/r13-3592 .
We've done it by using an artificial wrapper class for each of those and…
-
In CBOR library there are a couple of unidentified functions such as:
`unpack_float16`
```python
def decode_float16(decoder):
payload = decoder.read(2)
return unpack_float16(payload)
`…
-
**What is your question?**
It seems that add tile_description would make the gemm result different? `assert (tensor_D_numpy - tensor_D).max() == 0.0` would pass if I add tile_decription.
```
import …
-
Hi,
I am using your library for fast prototyping.
It was very convenient to use but i had to patch it to read float16.
`float16` is not supported by js, but is supported by webgl. So this all…