-
OOM occurs when quantifying DeepSeek model on 8XA800。
The code used comes from https://github.com/neuralmagic/AutoFP8/issues/29
```
from datasets import load_dataset
from transformers import Aut…
-
ValueError:
Some modules are dispatched on the CPU or the disk. Make sure you have enough GPU RAM to fit
the quantized mode l. If you want to dispatc…
-
### 一、BackGround 📚
任务背景、任务修改内容、提交样例可参考前期已发布过的任务：https://github.com/PaddlePaddle/Paddle/issues/58067
### 二、Task 📚
| 序号 | Python API | 所在文件 …
-
### Your current environment
The output of `python collect_env.py`
```text
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A…
-
### Your current environment
The output of `python collect_env.py`
```text
PyTorch version: 2.4.0+cu121
Is debug build: False
CUDA used to build PyTorch: 12.1
ROCM used to build PyTorch: N/A…
-
### 问题确认 Search before asking
- [X] 我已经查询[历史issue](https://github.com/PaddlePaddle/PaddleDetection/issues)，没有发现相似的bug。I have searched the [issues](https://github.com/PaddlePaddle/PaddleDetection/issu…
-
I recently upgraded my deployment from version 0.2.7 to 0.3.0 for a mixtral-8x7b architecture model and have encountered a significant issue where the model outputs completely garbled data post-upgr…
44670 updated
2 weeks ago
-
QUELQUES PROPOSITIONS DU FRONT NATIONAL
→ [12] Rétablir la sécurité en veillant à la protection des libertés individuelles.
→ [13] Réarmer massivement les forces de l’ordre : en personnels (plan d…
-
## 🐛 Bug
The just released Qwen2 has the same architecture as the previous Qwen1.5, so theoretically it should be able to run directly. In fact, the model was quantized and compiled without errors.…
-
### Search before asking
- [X] I have searched the YOLOv8 [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar bug report.
### YOLOv8 Component
_No response_
…