-
Hey @fchollet,
do you have any roadmap to implement sparse tensors for the different backends?
- tf seems to have only one implementation of sparse tensors [COO](https://www.tensorflow.org/guide/s…
-
**Describe the bug**
I'm compressing a qwen2.5_7b model using `examples/quantization_2of4_sparse_w4a16/llama7b_sparse_w4a16.py`, but I failed to load the stage_sparsity model. The error is shown belo…
-
When training with `02_train_network.py`, execution terminates with the error:
> RuntimeError: Batches of sparse tensors are not currently supported by the default collate_fn; please provide a cust…
-
Thanks for this nice repo.
**Describe the bug**
Finetuning in 2:4 sparsity w4a16 example fails with multiple GPUs
**Expected behavior**
The finetuning step expected to train successfully with …
-
**Describe the bug**
This is a minor issue, but I think the quantization configuration in the file `[examples/quantization_24_sparse_w4a16/2:4_w4a16_group-128_recipe.yaml]`(https://github.com/vllm-pr…
-
### 🚀 The feature, motivation and pitch
I am using torch as part of some code that solves quantum systems in a differentiable way. An important part of this process is constructing large sparse mat…
-
### Feature description
A tensor representation that only stores data for positions where the value non-zero. Operations on sparse tensors could then be optimized based on the fact that most of the t…
-
Hi!
It would be nice to have a way to assign values to the specific position in the sparse tensor.
Are there any workarounds that allow to set a values to the specific index?
-
Hi @nullplay,
I wanted to start a discussion on Finch-MLIR MLIR tensors API. In https://github.com/pydata/sparse/tree/main/sparse/mlir_backend we have an initial Tensor class which provides constr…
-
this is the code:
```
import torch
from pytorch_block_sparse import BlockSparseLinear
x = torch.randn(32, 128).to('cuda')
y = torch.randn(32, 64).to('cuda')
model = torch.nn.Sequential(
…