How does this compare to PyTorch labs optimizations for Sam and llama2 ? https:/... | Hacker News

Hacker Newsnew | past | comments | ask | show | jobs | submit

		naveen99 on Dec 2, 2023 \| parent \| context \| favorite \| on: Show HN: 80% faster, 50% less memory, 0% loss of a... How does this compare to PyTorch labs optimizations for Sam and llama2 ? https://github.com/pytorch-labs/segment-anything-fast https://github.com/pytorch-labs/gpt-fast

danielhanchen on Dec 3, 2023 [–]

Hey! That's for inference - our code is for training :) We do plan faster inference in the future!! Saw GPT Fast by Chillee - it is blazingly fast!

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact