-
### Problem Description
Composable Kernel currently only contains code to support fused attention (FA2) on RDNA3(+) architectures in the forward direction. This greatly increases the VRAM requirement…
-
Hi,
Thank you for your great work and nice repo. I was able to run the code on an A100 machine but had difficulties running it on a V100 machine. I was wondering if the kernels are runnable on V100…
-
### Required prerequisites
- [X] Search the [issue tracker](https://github.com/NVIDIA/cuda-quantum/issues) to check if your feature has already been mentioned or rejected in other issues.
### Descri…
-
**Project description**
CachyOS is an Arch Linux-based distribution focused on performance and customizability
**Metadata**
* homepage URL: [https://cachyos.org](https://cachyos.org)
* source …
-
Hi!
I am getting a bunch of linker errors, appearing to be circular imports. I am using TFLM_ESP32 v2.0 and EloquentTinyML 3.0.1
Thanks in advance.
Linking everything together...
/home/alvaro…
-
Currently, a kernel library can be assembled only from a single module. For complex kernels (e.g., the transaction kernel in `miden-base`), this means that to avoid having one giant file we need to in…
-
Is there a recipe for building custom Jupyter Desktop installers that bundle alternative kernels?
I am looking to distribute JupyterLab-Desktop to users in a limited permissions secure environment …
-
I'm using Kaggle API version 1.6.17. I noticed the `model_sources` field in the kernel-metadata.json file is ignore when using` kaggle kernel push` CLI command. I tried it both with creating new kerne…
-
Something that's been under discussion for a while now is splitting off the scalar kernels for ufuncs and gufuncs in `scipy.special` into a separate library. The plan would be for this library to stil…
-
### 🚀 The feature, motivation and pitch
I'm working on benchmarking some custom triton kernels and different PyTorch operator implementations for inductor improvement.
Here are the goals
- [ ] …