Inferencemaxxing

AI Inference learnings


Experiments (Threads/Blogs/Articles)

#TopicLink
1Inference comparisonPyTorch vs vLLM — Qwen2.5-1.5B-Instruct Comparison
2kv cacheWhy do we need KV cache?
3prefill and decodeWhat actually happens inside an LLM when you send a prompt?

Learning Resources