-
Hello, I want to use TPOT for feature engineering. Therefore, I chose a fixed model for TPOT like a linear regression model and the default configuration.
Having some features {x1,x2,…}, there are …
-
It is often useful to define linear operators on arbitrary linear spaces, not necessarily AbstractVectors (e.g. the discretization of a n-d PDE). At the moment this is not supported by LinearMaps.
-
### Situation ###
Operator classes like `Matrix` or `MatrixSymbol` represent scalar results as multiple of their respective Identity operator, i.e. operator * operator -> operator (except for 0):
``…
-
# Description
Current challenges in using Neural Operators are: irregular meshes, multiple inputs, multiple inputs on different meshes, or multi-scale problems. [1] The Attention mechanism is promi…
-
I'm currently using v2.3.1 but after looking at the current version, the problem is still there.
`operator+` is defined like:
```cpp
template = 0>
constexpr inline int operator+(const UnitTypeLh…
-
Multilinear operators (tensors) appear in quadratic systems. If a linear system is
```
x' = A x + B u,
y = C x,
```
a quadratic system would be
```
x' = A x + H^(1) (x kron x) + B u,
y = C x.
```
…
-
# Bug Report
**Orion version:** 0.2.5
**Current behavior:** not compiled
**Expected behavior:** compiled
**Steps to reproduce:**
```bash
git clone git@github.com:gizatechxyz/…
-
## 🚀 Feature
PyTorch has operators that create tensor views for buffer sharing. We'd like to have a JIT pass that can replace these alias operators with functional equivalents that do not have the …
-
### Idea
Use int4 as the compression technique to fit larger models onto Navi machines or possibly MI series machines. Weights would be compressed using encoding scheme that would pack two 4 bits n…
-
# RFC: Integration of KleidiAI 4-Bit MatMul Kernels into PyTorch
**Hardware Platform**: aarch64
## Motivation
1. Add support for [KleidiAI](https://gitlab.arm.com/kleidi/kleidiai) 4-bit matrix …
ng-05 updated
1 month ago