skyzh/tiny-llm

• highreadme#1

  Clarify README's opening paragraph to emphasize "course" and "Python"

  原因：

  当前

  A course on LLM serving using MLX for system engineers. The codebase is solely (almost!) based on MLX array/matrix APIs without any high-level neural network APIs, so that we can build the model serving infrastructure from scratch and dig into the optimizations.

  复制粘贴的修复

  复制

  This is a hands-on course for system engineers to learn LLM inference serving on Apple Silicon. You will build a tiny vLLM-like system and Qwen model from scratch, entirely in Python, using MLX array/matrix APIs to understand the underlying optimizations.

  待办完成忽略
• hightopics#2

  Add specific topics for platform, learning style, and domain

  原因：

  当前

  course, large-language-model, llm, python, qwen, qwen2, serving, vllm

  复制粘贴的修复

  复制

  course, large-language-model, llm, python, qwen, qwen2, serving, vllm, apple-silicon, macos, llm-inference, from-scratch, educational

  待办完成忽略
• mediumabout#3

  Refine the repository description to emphasize "Python" and "from scratch"

  原因：

  当前

  A course of learning LLM inference serving on Apple Silicon for systems engineers: build a tiny vLLM + Qwen.

  复制粘贴的修复

  复制

  A hands-on course for systems engineers to learn LLM inference serving on Apple Silicon, building a tiny vLLM-like system and Qwen model from scratch using Python.

  待办完成忽略

本次扫描解析到的品类 GEO 通道：google/gemini-2.5-flash, deepseek/deepseek-v4-flash

• 品类问题

  How to learn building large language model inference systems on macOS?

  你：未被推荐
  AI 推荐顺序：

  1. Hugging Face Transformers
  2. Optimum
  3. PyTorch's Metal Performance Shaders (MPS)
  4. bitsandbytes
  5. llama.cpp (ggerganov/llama.cpp)
  6. llama-cpp-python
  7. Ollama
  8. MLX (apple/mlx)
  9. vLLM

  AI 推荐了 9 个替代方案，却始终没点名 skyzh/tiny-llm。这就是要补上的差距。

  查看 AI 完整回答
• 品类问题

  Seeking a course to build custom LLM serving infrastructure from scratch using Python.

  你：未被推荐
  AI 推荐顺序：

  1. LangChain
  2. FastAPI
  3. Docker
  4. Google Cloud
  5. Flask

  AI 推荐了 5 个替代方案，却始终没点名 skyzh/tiny-llm。这就是要补上的差距。

  查看 AI 完整回答

• Metadata completeness

  pass

• README presence

  pass

• Compared to common alternatives in this category, what is the core differentiator of skyzh/tiny-llm?

  pass
  ⚠AI 未点名 skyzh/tiny-llm —— 很可能在说另一个项目

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• If a team adopts skyzh/tiny-llm in production, what risks or prerequisites should they evaluate first?

  pass
  ✓AI 明确点名了 skyzh/tiny-llm

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？

• In one sentence, what problem does the repo skyzh/tiny-llm solve, and who is the primary audience?

  pass
  ✓AI 明确点名了 skyzh/tiny-llm

  AI 的回答可能信誓旦旦却是错的。请按事实核对：技术栈、目标人群、差异化点是不是和你实际的对得上？