Raymond Cheng

Results 3 comments of Raymond Cheng

Any update to this problem? Having exactly the same issue here.

Yes same here for us. Both huggingface and this repo seem to have the same OOM error when running on Google Colab free GPU like p100. Any fix or workaround...

@casper-hansen Hi, I'm meeting this same issue. To unblock, would you mind sharing which previous version of AutoAWQ works with vLLM?