-
Error occurred when executing Miaoshouai_Tagger:
Using `low_cpu_mem_usage=True` or a `device_map` requires Accelerate: `pip install accelerate`
File "C:\ComfyUI-Zluda\execution.py", line 317, in…
-
💻 **Feature request: Numba acceleration**
What else can be said? At the moment, the package does not provide a Numba accelerated code because although useful, it can become tricky for particular ty…
-
```
Alpha compression is much faster than color compression, alpha blocks could
be compressed in parallel on the CPU. However, on GT200 CUDA color
compression is faster than alpha CPU compression, and…
-
```
Alpha compression is much faster than color compression, alpha blocks could
be compressed in parallel on the CPU. However, on GT200 CUDA color
compression is faster than alpha CPU compression, and…
-
I found the calculation of the reading pipeline is super slow. I send the projection and recenter to GPU and make it run 20x faster. May I open a pull request?
```
def project_onto_direction(H, dire…
-
### Describe the bug
I am using the training script documented here https://github.com/huggingface/diffusers/blob/main/examples/dreambooth/README_flux.md to train a LORA on my dataset.
here is th…
-
```
Alpha compression is much faster than color compression, alpha blocks could
be compressed in parallel on the CPU. However, on GT200 CUDA color
compression is faster than alpha CPU compression, and…
-
```
Alpha compression is much faster than color compression, alpha blocks could
be compressed in parallel on the CPU. However, on GT200 CUDA color
compression is faster than alpha CPU compression, and…
-
meshing is expensive, but should just be linear algebra, should figure out if we can hardware accelerate algorithms like these: https://docs.scipy.org/doc/scipy-0.14.0/reference/generated/scipy.spatia…
-
Tensor Cores are used
but still 1 second / step , just like no tensor cores .