📄 文章列表
435 篇文章
TDS
A Guide to Understanding GPUs and Maximizing GPU Utilization
TDS
RAG Isn’t Enough — I Built the Missing Context Layer That Makes LLM Systems Work
TDS
Prefill Is Compute-Bound. Decode Is Memory-Bound. Why Your GPU Shouldn’t Do Both.
TDS
6 Things I Learned Building LLMs From Scratch That No Tutorial Teaches You
TDS
Your RAG System Retrieves the Right Data — But Still Produces Wrong Answers. Here’s Why (and How to Fix It).
TDS
KV Cache Is Eating Your VRAM. Here’s How Google Fixed It With TurboQuant.
TDS
Dreaming in Cubes
TDS
Bytes Speak All Languages: Cross-Script Name Retrieval via Contrastive Learning
TDS
PyTorch NaNs Are Silent Killers — So I Built a 3ms Hook to Catch Them at the Exact Layer
TDS
Ensembles of Ensembles of Ensembles: A Guide to Stacking
TDS
RAG Hallucinates — I Built a Self-Healing Layer That Fixes It in Real Time
TDS
Timer-XL: A Long-Context Foundation Model for Time-Series Forecasting
TDS
The Must-Know Topics for an LLM Engineer
TDS
Using Transformers to Forecast Incredibly Rare Solar Flares
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
Deploying a Multistage Multimodal Recommender System on Amazon Elastic Kubernetes Service
TDS
From TF-IDF to Transformers: Implementing Four Generations of Semantic Search
TDS
EmoNet: Speaker-Aware Transformers for Emotion Recognition — and What I’d Build Differently in 2026
TDS