Article
Prefill and Decode for Concurrent Requests - Optimizing LLM Performance
tngtech
• • 87
Sankalp
dejavucoder
AI & ML interests
LLM architecture
Applied AI
Organizations
upvoted an article 9 months ago
upvoted 3
articles about 2 years ago
Article
SmolLM - blazingly fast and remarkably powerful
- +1
loubnabnl, anton-l, eliebak
• • 464 Article
Fine-tune Llama 3.1 Ultra-Efficiently with Unsloth
mlabonne
• • 373 Article
Shape Rotation 101: An Intro to Einsum and Jax Transformers
dejavucoder
• • 4 upvoted 3
articles over 2 years ago
Article
How to Finetune phi-3 on MacBook Pro
abhishek
• • 68 Article
Better RAG 1: Advanced Basics
hrishioa
• • 35 Article
Mixture of Depth is Vibe
joey00072
• • 48