Illustration drawn by RepoMasters from the repo’s ID and its language color. Credits
AlphaUncommon

PotatoSpudowski/fastLLaMa

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

Owner
PotatoSpudowski (personal account)
Stars
Stars: 412
Forks
Forks: 25
Language
C
License
MIT
Created
2023
Topics
lamapythonlamacppccpp
Tier
Alpha (250 to 699 ★) What this tier means
View on GitHub

More repos by PotatoSpudowski

All 2 repos by PotatoSpudowski

Nearby in C

All C repos