Llama 2 inference implementations
6 repos
Lightweight, single-file implementations of Llama 2 model inference across multiple programming languages including C, Python, TypeScript, JavaScript, and Zig. These repositories focus on making LLM inference accessible and portable by providing minimal, educational implementations that can run efficiently on consumer hardware, often with SIMD optimizations. A learner exploring this cluster would see how the same inference algorithm translates across different language ecosystems and performance trade-offs.
C# · 1
JavaScript · 1
Jupyter Notebook · 1
Python · 1
Rust · 1
Zig · 1
llama2 ·2,281
llm-inference ·2,178
llm ·2,178
llama-2 ·1,936
llama ·325
ziglang ·222
simd ·222
zig ·222
csharp ·103
tinystories ·20
