-
Add:
`LLSparseMatrix` `A` with:
- [x] `LLSparseMatrix` `B`: `A * B` and `A^t * B`;
- [x] `NumPy` `B`: `A * B` and `A^t * B`;
- [ ] `NumPy` `B`: `B * A` and `B * A^t`;
- [ ] `CSRSparseMatrix` `B`: `A …
ghost updated
9 years ago
-
When I comment out this line https://github.com/openai/triton/blob/db6935c300508cc1f3933059c70c87ba4f0221ee/python/triton/testing.py#L141, triton becomes very time-consuming? Why
-
### 🚀 The feature, motivation and pitch
I want to do a sort of batched sparse-sparse matrix multiplication, but specifically in the scenario where I have two hybrid sparse coo tensors of the shape (N…
-
### 🚀 The feature, motivation and pitch
We know that language models exhibit activation sparsity during inference, meaning that they can perform lossless inference even when only a portion of the act…
-
Hello, when experimenting further with the library, I found that the following snippet:
```
#include
#include
#include
#include
#include
#include
void test_psst_math()
{
usin…
-
-
## Description:
The dense matrix format is the most straightforward format to implement, but will occur a lot of unnecessary storage cost if the sparsity is high. The dense matrix format is an explic…
-
### 🚀 The feature, motivation and pitch
3D fp8 matrix multiplication can be useful for fp8 model with 3D matmul (it also can be used to improve accuracy of models with 2D fp8 quantized matrix multi…
-
Hi, I noticed that the dataset for the neural network consists of a covariance matrix (call it R_tau) and the true doa (denoted by Y). It is then fed into the DNN.
However, the output of the DNN need…
-
Please make sure that this is a bug. As per our
[GitHub Policy](https://github.com/tensorflow/tensorflow/blob/master/ISSUES.md),
we only address code/doc bugs, performance issues, feature requests a…