CONTEXT CACHING for Faster and Cheaper Inference
40:40
How to use LLMs for Fact Checking
24:23
Output Predictions - Faster Inference with OpenAI or vLLM
49:45
Modèles et techniques d'intégration avancés pour RAG
9:18
Reacting to Controversial Opinions of Software Engineers
53:31
Charlie Snell, UC Berkeley. Title: Scaling LLM Test-Time Compute
54:16
Agents de récupération – Trois leçons apprises !
6:23
Paying for software is stupid… 10 free and open-source SaaS replacements
1:00:38