Article
Efficient Request Queueing – Optimizing LLM Performance
tngtech
• • 26chen
2395959141pq
·
AI & ML interests
生成式AI ， CV
Organizations
None yet
upvoted 2
articles 9 months ago
Article
Prefill and Decode for Concurrent Requests - Optimizing LLM Performance
tngtech
• • 78 upvoted 2
articles 12 months ago
Article
A Gentle Introduction to 8-bit Matrix Multiplication for transformers at scale using transformers, accelerate and bitsandbytes
ybelkada, timdettmers
• • 132 Article
Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRA
- +3
ybelkada, timdettmers, artidoro, sgugger, smangrul
• • 180 upvoted an article about 1 year ago
Article
Mixture of Experts Explained
- +4
osanseviero, lewtun, philschmid, smangrul, ybelkada, pcuenq
• • 1.13k