Suggest an alternative to

fastLLaMa

fastLLaMa: An experimental high-performance framework for running Decoder-only LLMs with 4-bit quantization in Python using a C/C++ backend.

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 fastLLaMa. Optional.

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