Halo Master

Chinese output is garbled!

1

First of all, thank you for providing such a great open source project! I tried the default model in the README, everything is OK, except when I want the model...

遇到奇怪的报错

1

> python web_demo.py chatglm [i 0510 05:25:05.380000 16 compiler.py:955] Jittor(1.3.7.15) src: e:\anaconda3\lib\site-packages\jittor [i 0510 05:25:05.539000 16 compiler.py:956] cl at C:\Users\linke\.cache\jittor\msvc\VC\_\_\_\_\_\bin\cl.exe(19.29.30133) [i 0510 05:25:05.540000 16 compiler.py:957] cache_path: C:\Users\linke\.cache\jittor\jt1.3.7\cl\py3.10.9\Windows-10-10.x9e\IntelRCoreTMi5x25\default [i 0510 05:25:05.569000...

cli_demo.py chatglm demo报错

14

环境： win 10 ananconda python 3.10 CUDA 11.7.1 jTorch 已经安装 ---------------------------------- 出错信息： ``` shell PS G:\pys\JittorLLMs> python cli_demo.py chatglm [i 0417 02:47:56.967000 52 compiler.py:955] Jittor(1.3.7.13) src: e:\anaconda3\lib\site-packages\jittor [i 0417 02:47:57.020000...

在Windows系统上使用GPU进行模拟时，遇到 `operation not supported` 错误通常是由于Windows不支持CUDA tensor上的多进程操作。这是一个已知问题，因为CUDA多进程支持在Windows上的实现存在一些限制。然而，有一些解决方案可以帮助解决或绕过这个问题。 ### 解决方案 #### 1. 使用单进程来处理CUDA操作 如果多进程是为了并行计算，可以考虑在单个进程中使用并行库，如CUDA Streams或PyTorch的DataLoader中的多线程模式。这可以避免多进程的限制。 ```python import torch from torch.utils.data import DataLoader # 使用DataLoader的多线程模式 data_loader = DataLoader(dataset, batch_size=64, shuffle=True, num_workers=4, pin_memory=True) for...

running on browsers ? (webassembly?)

2

It would be really cool if the tview project could run in a browser just like gio!

Upgrade 1.3.4 and failed to login

8

reinstall and delete and register and failed

[Prompt]Template of prompts

1

**What problem or use case are you trying to solve?** [The cooragent project has a powerful template-system of prompts. ](https://deepwiki.com/LeapLabTHU/cooragent/4.1-prompt-system) Could we merge these to OpenHands? **Describe the UX or...