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
More repos by PotatoSpudowski
All 2 repos by PotatoSpudowski- PotatoSpudowski/RUL-and-SOH-estimation-of-Lithium-ion-satellite-power-systems-using-support-vector-regressionStars: 109Jupyter NotebookPrototype
Nearby in C
All C repos- Al1ex/LinuxEelvationStars: 412CAlpha
- google/eshStars: 412CAlpha
- Swung0x48/TriangleBinStars: 412CAlpha
- kfish/xselStars: 412CAlpha
- berkeleydb/libdbStars: 412CAlpha
- libretro/parallel-n64Stars: 412CAlpha