Pinned Loading

1. mini-vllm mini-vllm Public

   A minimal vLLM-style LLM inference engine for Apple Silicon, built on MLX.

   Python

2. llm-from-scratch llm-from-scratch Public

   Forked from stanford-cs336/assignment1-basics

   Implementation of a Large Language Model From Scratch - Stanford CS336

   Python

3. llm-gateway llm-gateway Public

   Smart proxy layer between clients and LLM providers — routing, caching, rate limiting, cost control, observability

   Go

4. CacheSystem CacheSystem Public

   High concurrency cache system implemented in C++. Utilized optimized LRU, LFU, ARC algorithms for data eviction.

   C++

5. WLP4Compiler WLP4Compiler Public

   A compiler for WLP4 programming languages (a subset of C). The compiler implemented scanner, parser, semantic analyzer, and code generator from scratch using C++.

   C++

6. KingDavidKo/Expense-App KingDavidKo/Expense-App Public

   Kotlin 1