fastLLaMa

fastLLaMa

PotatoSpudowski

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

c-plus-plus
View on GitHub Website
373 Stars
24 Forks
373 Watchers
C Language
mit License
Cost to Build
$633.0K
Market Value
$1.30M
How is this calculated?

Growth over time

1 data points  ·  2023-07-07 → 2023-07-07
Stars Forks Watchers
💬

How do you feel about this project?

Ask AI about fastLLaMa

Question copied to clipboard

What is the PotatoSpudowski/fastLLaMa GitHub project? Description: "fastLLaMa: An experimental high-performance framework for running Decoder-only LLMs with 4-bit quantization in Python using a C/C++ backend.". Written in C. Explain what it does, its main use cases, key features, and who would benefit from using it.

Question is copied to clipboard — paste it after the AI opens.

🏆 Show off this rank

PotatoSpudowski/fastLLaMa on SrcLog (holo style)

Add it to a GitHub README or profile — the card updates as the ranking changes:

How to clone fastLLaMa

Clone via HTTPS

git clone https://github.com/PotatoSpudowski/fastLLaMa.git

Clone via SSH

[email protected]:PotatoSpudowski/fastLLaMa.git

Download ZIP

Download master.zip

Found an issue?

Report bugs or request features on the fastLLaMa issue tracker:

Open GitHub Issues

Similar to fastLLaMa

awesome-cpp project-based-learning infer openpose openage solidity tinyrenderer modern-cpp-features LeetCode yuzu dolphin compiler-explorer antlr4 BackgroundMusic citra vcpkg cython aleth cpprestsdk MuseScore modern-cpp-tutorial pcl milewski-ctfp-pdf awesome-modern-cpp osrm-backend javacpp pcsx2 algorithms_and_data_structures arrayfire conan