wskwon

Thanks! Please try it out and share any feedback you might have.

Thanks for the explanation! I believe the two ideas are basically orthogonal. FlashAttention reduces memory read/writes, while PagedAttention reduces memory waste.

wskwon

3 anni fadiscuss

Yes, vLLM focuses on maximizing throughput when the VRAM is fully utilized. Nevertheless, I believe users can still benefit from vLLM even if they don't utilize the memory to its full capacity, because vLLM also includes other optimizations orthogonal to the PagedAttention (e.g., optimized CUDA kernels).

wskwon

3 anni fadiscuss

We used matplotlib for the performance charts, and used a free website to convert google slides to the animation gifs.

wskwon

3 anni fadiscuss

Not really. vLLM optimizes the throughput of your LLM, but does not reduce the minimum required amount of resource to run your model.

wskwon

3 anni fadiscuss

You can think of LMSYS Vicuna: https://chat.lmsys.org as our hosted demo, as it actually uses vLLM as the backend.

wskwon

3 anni fadiscuss

vLLM has been adopted by LMSYS for serving Vicuna and Chatbot Arena.

Submissions

vLLM: Easy, Fast, and Cheap LLM Serving with PagedAttention

comments