mycpuorg

nd array shape modified with benchmark ??

1

I'm trying to run pytest benchmark on an application that uses mxnet backend. I'm running the application: https://github.com/apache/incubator-mxnet/blob/master/example/recommenders/demo1-MF.ipynb Specifically, I want to benchmark the calls to train() function (in the...

Hi, I have a relatively straightforward situation where I need to validate my input shapes while `jit.load`ing a saved model and I can't seem to find the solution for. ```python...

I love the idea of this library. I would prefer to use it but the following simple usecase fails in unexpected ways: ``` pipes::mux(tags, res) >>= pipes::filter([&](auto t, auto r)...

Hey there :wave: Just wanted to let you know that [your app on Streamlit Cloud deployed from this repo](https://jbloomaus-decisiontransformerinterpretability-app-4edcnc.streamlit.app/jbloomaus/decisiontransformerinterpretability/main/app.py) has gone over its resource limits. Access to the app is...

Reproduce Deepseek GEMM perf in tk

5

 Would be great to see tk implementation to understand how to achieve Deepseek levels of perf here even if it's for academic purposes only.