-
This is a new issue to discuss performance optimization for sampling of alternatives in the `MergedChoiceTable` utility.
Earlier discussion is in issues #4, #5, and #11, now closed. Core functional…
-
Status: Draft
Updated: 09/18/2024
# Objective
In this doc we’ll talk about how different optimization techniques are structured in torchao and how to contribute to torchao.
# torchao Stack Ove…
-
A fundamental limitation of our auto diff tool JAX is it is [unable to handle dynamic size arrays](https://github.com/jax-ml/jax/discussions/18790) or jagged tensor operations. Both of these operation…
-
Hi,
Awesome work!
I would like know more about 3DMM work. I tried to generate them with a 3dmm model. But didn't get accuracy. Which 3DMM model did you used?
-
-
The RyuJIT emitter uses a machine-level program representation which is not designed for modification after it is generated, such as modification due to peephole optimization or other low-level code t…
-
Thanks for the great work here. It's really exciting to be able to try out mixed-precision so easily now in PyTorch.
Currently I'm training a GPU image classification model (resnet101) but for extr…
-
So far my application is working very well and will run for several hours (and days) with no problems and excellent keyword recognition.
However, it will occasionally "stop listening" for several mi…
-
Environment: `Linux 6.5.0-26-generic #26~22.04.1-Ubuntu`
Consider following minimal example:
```
@time_hash = {}
def perf_time(id)
@time_hash[id] = Time.now
end
def perf_time_end(id)
…
-
In the user guide of NOMAD they said that NOMAD will be able to handle biobjective function also. Is it possible in our NOMAD.jl also?