Writing
- WarpQuant: Dual-Domain Low-Bit LLM Quantization
A post-training quantization method that reaches INT2/INT3 SOTA accuracy and runs the compressed weights directly through a C++/CUDA llama.cpp kernel β 7.36Γ faster decoding than GPTQ W3.
- Building a Production LangGraph Travel Agent
How I built a LangGraph travel assistant that searches flights, hotels, and activities in parallel and assembles budget-aware packages.
- Modern Anti-Bot Systems and How to Bypass Them
An engineering deep-dive into web scraping in 2025, with a production case study.
No posts match.