qinzhenyi

it works for me too, thanks!

遇到了同样的问题，请问有解决吗？

已经解决了吗？同样遇到了这个错误~

> > 已经解决了吗？同样遇到了这个错误~ > > torch 换1.8的版本 我这边换成1.8的版本，解决了

@poppp234 你好按图片在前的方式，显示500报错了 如果单纯问一段文字是正常的~   `INFO: 10.0.10.7:20191 - "POST /v1/chat/completions HTTP/1.1" 500 Internal Server Error ERROR: Exception in ASGI application Traceback (most recent call last): File "/home/work/miniconda3/envs/Qwen-VL-Chat/lib/python3.10/site-packages/uvicorn/protocols/http/h11_impl.py", line 407, in...

同问，多种方式都尝试都显示 **RuntimeError: Triton Error [CUDA]: device kernel image is invalid** 方法一、cogvlm本事可以正常跑的环境（torch2.3.0+cuda11.8），运行cogvlm2显示Triton报错 方法二、从零开始conda安装

> torch2.3.0+cu121尝试一下 服务器限制，不能升级驱动，不能使用cu121，之前cogvlm使用cuda11.8是可以的，新的cogvlm2 ，同样的环境 RuntimeError: Triton Error [CUDA]: device kernel image is invalid

it still reported errors after I successfully run the above command, the reason why I python test because I encountered an error **Triton Error [CUDA]: device kernel image is invalid**...

the error in my llm project File "/opt/conda/lib/python3.10/site-packages/torch/nn/modules/module.py", line 1520, in _call_impl return forward_call(*args, **kwargs) File "/opt/conda/lib/python3.10/site-packages/accelerate/hooks.py", line 166, in new_forward output = module._old_forward(*args, **kwargs) File "/root/.cache/huggingface/modules/transformers_modules/119df232ab9fca4a1be87f95c239d7b9a765032e/util.py", line 469, in...

I have this error too，and i use @Eralaf method to check xml finally，i Found the cause of the mistake ` if not self.keep_difficult and difficult: continue` Original code dose not...