Tag: performance

6 posts

Aug 4, 2026 How I would design an LLM inference API in a system design interview
Aug 4, 2026 Notes on inference architecture: the trade-offs don't transfer
Aug 3, 2026 Reading kimi-k3-in-c: 2.8T parameters in 8GB of RAM
Jul 30, 2026 Why some AI demos resolve text instead of typing it
Mar 28, 2024 TILs at Snowflake
Jul 31, 2021 Tech recordings at Amazon