📄 文章列表
313 篇文章
TDS
Prefill Is Compute-Bound. Decode Is Memory-Bound. Why Your GPU Shouldn’t Do Both.
TDS
Introduction to Deep Evidential Regression for Uncertainty Quantification
TDS
What It Actually Takes to Run Code on 200M€ Supercomputer (HPC & SLURM)
TDS
Your RAG System Retrieves the Right Data — But Still Produces Wrong Answers. Here’s Why (and How to Fix It).
TDS
Your RAG Gets Confidently Wrong as Memory Grows – I Built the Memory Layer That Stops It
TDS
How to Call Rust from Python
TDS
PyTorch NaNs Are Silent Killers — So I Built a 3ms Hook to Catch Them at the Exact Layer
TDS
Playing Connect Four with Deep Q-Learning
TDS
How to Build an Efficient Knowledge Base for AI Models
TDS
RAG Hallucinates — I Built a Self-Healing Layer That Fixes It in Real Time
TDS
I Rewrote a Real Data Workflow in Polars. Pandas Didn’t Stand a Chance.
TDS
RAG Is Blind to Time — I Built a Temporal Layer to Fix It in Production
TDS
Hybrid Search and Re-Ranking in Production RAG
TDS
LLM Evals Are Based on Vibes — I Built the Missing Layer That Decides What Ships
TDS
Proxy-Pointer RAG: Solving Entity and Relationship Sprawl in Large Knowledge Graphs
TDS
Prompt Engineering Isn’t Enough — I Built a Control Layer That Works in Production
TDS
The Infrastructure Behind Making Local LLM Agents Actually Useful
TDS
Five Questions About Chronos-2, the Time Series Foundation Model
TDS
RAG Is Burning Money — I Built a Cost Control Layer to Fix It
TDS