Suggest an alternative to

exllamav2

A fast inference library for running LLMs locally on modern consumer-class GPUs

Why do you think that https://github.com/FasterDecoding/Medusa is a good alternative to exllamav2

A URL to the alternative repo (e.g. GitHub, GitLab)

Here you can share your experience with the project you are suggesting or its comparison with exllamav2. Optional.

A valid email to send you a verification link when necessary or log in.