| Title | pytorch pytorch (torch.nn.utils.rnn.unpack_sequence) torch 2.6.0 Segmentation fault |
|---|
| Description | # Bug Description
Calling `unpack_sequence` on an empty PackedSequence leads to a segmentation fault.
# Reproduction Steps
Run the following code:
```
import torch
from torch.nn.utils.rnn import PackedSequence, unpack_sequence
empty_data = torch.tensor([])
empty_batch_sizes = torch.tensor([], dtype=torch.int64)
packed = PackedSequence(data=empty_data, batch_sizes=empty_batch_sizes)
unpack_sequence(packed)
```
# Observed Behavior
The program crashes with a segmentation fault, indicating an invalid memory access. |
|---|
| Source | ⚠️ https://github.com/pytorch/pytorch/issues/149622 |
|---|
| User | Default436352 (UID 81891) |
|---|
| Submission | 20/03/2025 15h43 (há 4 meses) |
|---|
| Moderation | 30/03/2025 19h42 (10 days later) |
|---|
| Status | Aceite |
|---|
| VulDB Entry | 302048 [PyTorch 2.6.0 torch.nn.utils.rnn.unpack_sequence Excesso de tampão] |
|---|
| Points | 20 |
|---|