ValueError: Found modules on cpu/disk. Using Exllama backend requires all the modules to be on GPU.You can deactivate exllama backend by setting `disable_exllama=True` in the quantization config objec

[dinchu]

when trying to load quantized models i always get

ValueError: Found modules on cpu/disk. Using Exllama backend requires all the modules to be on GPU.You can deactivate exllama backend by setting disable_exllama=True in the quantization config objec

[aliozts]

Hi, may I ask how do you load the model, in my case with single GPU I also had that problem and I had to use disable_exllama=True while loading the model (change the config.json in your model file and add disable_exllama: true to quantization_config there if you're loading it directly from a file). When I worked with 2 GPUs, I did not have this problem. Sorry if it does not answer your question but I hope it helps. I do not know why this happens though sadly.

[ilovesouthpark]

It can work, Thanks. @aliozts

[tigerinus]

Hi, may I ask how do you load the model, in my case with single GPU I also had that problem and I had to use disable_exllama=True while loading the model (change the config.json in your model file and add disable_exllama: true to quantization_config there if you're loading it directly from a file). When I worked with 2 GPUs, I did not have this problem. Sorry if it does not answer your question but I hope it helps. I do not know why this happens though sadly.

Disabling Exllama makes the entire inferencing much slower.

Check out https://github.com/PanQiWei/AutoGPTQ/issues/406 for how to enable Exllama.

[Saravan004]

Why I cant run it in GPU? Although I am having NVIDIA GeForce Mx450. Could anyone please help?

[apoorvpandey0]

I have NVIDIA GTX 1650 still getting same error

[chenyujiang11]

在config.json的quantization_config下加入"disable_exllama": true，即可解决问题。 这个错误只有单卡的时候才会出现，多卡时未出现过，使用的显卡为Tesla T4。

[UmiVilbig]

I was running into a similar problem running GPTQ in a docker container. I was getting disable_exllama error. In short the issue showed up when I ran the container without --gpus all command. Below is my system configs

GPU: 1660Ti transformers==4.36.2 optimum==1.16.1 auto-gptq==0.6.0+cu118 CUDA=12.3

SOLUTION: for me I fixed the disable_exllama error by running the container with --gpus all

[NamburiSrinath]

I am also facing the same issue. Disabling exllama increases the inference speed a lot, so am not sure if that's the ideal way.

Here are more details - https://github.com/lm-sys/FastChat/issues/3530

[kj-1024]

我遇到了同样问题，我使用dbgpt项目启动模型Qwen2.5-32B-Instruct-GPTQ-Int4报错如题目所述。定位到config.json文件，将use_exllama该项从true修改为false可解决。 希望对此有帮助。

[Monesi-dev]

I am still getting the same ValueError even if I have added "disable_exllama": true in the config.json of my model