[vladf]

Err, you are just restating what I’m saying, without addressing the concerns.

1 - is it fair to use ram in two places and report only one of them without any asterisk? (If you think this is fair-oh boy wait till you hear about my 0GB hbm use inference algorithm)

2 - i know how subchannel quantization works. Are they hitting those reported latency numbers with per layer cpu pingpong to rescale?

[danielhanchen]

Oh sorry - did not expect to restate what you said whoops - all train of thought!

You can see from https://huggingface.co/mobiuslabsgmbh/Llama-2-7b-chat-hf_1bi... that the model disk space is 3GB + 100MB of LoRA weights. I also uploaded a 4bit one to https://huggingface.co/unsloth/llama-2-7b-bnb-4bit/tree/main which uses 3.87GB.

So because of the offloading trick, the GPU VRAM is less, but in actuality, still 3GB is needed.

Unsure on latency sadly

[mobicham]

Hey Daniel! The VRAM is still the same as a pure n-bit model would take. Because we only need meta-data for a single nn.Linear at a time, you only need an additional (3GB-1.7GB)/224 = 5.8MB. If we compress the meta-data as well that would become much lower.