ssheng

قبل سنتينdiscuss

To get a full A10, one must also get 36 vCPU and 440 GB of memory. I must be missing something.

قبل سنتينdiscuss

Quality loss with quantization is expected. It seems like with GPTQ the loss is within acceptable range based on the perplexity score shown.

قبل سنتينdiscuss

How does Exllama rank among these? Heard good things about it.

قبل سنتينdiscuss

Creative idea. Any data on how much it takes to load the LoRAs and how much latency it adds to the generation speed?

قبل سنتينdiscuss

Hello! We're the authors of this blog post. Please let us know if there are other models and inference backends you'd like us to benchmark next.

Submissions