DeepSeek V3, SGLang, and the state of Open Model Inference in 2025 (Quantization, MoEs, Pricing)

4.6K views
•
January 19, 2025
by
Latent Space
YouTube video player
DeepSeek V3, SGLang, and the state of Open Model Inference in 2025 (Quantization, MoEs, Pricing)

Transcript

hey everyone welcome back to the laden space podcast our first recording of 2025 I'm alesio partner and CTO at desable partners and I'm joined by my co-host swix founder of small AI hey and today we are here with a special double guest episode with Amir oh my God I don't know your last hagat that's close enough that is good go that's really good an... Read More

Explore YouTube Video Summarizer or Get YouTube Transcript Extractor

Read in Other Languages (beta)

English

Share This Summary 📚

Explore More Summaries from Latent Space 📚

What is ARC AGI V3 interactive benchmark design? thumbnail
What is ARC AGI V3 interactive benchmark design?
Latent Space
How Does Factory AI Automate Enterprise Coding? thumbnail
How Does Factory AI Automate Enterprise Coding?
Latent Space
The Utility of Interpretability — Emmanuel Amiesen thumbnail
The Utility of Interpretability — Emmanuel Amiesen
Latent Space
How does RL verify science data in wet labs? thumbnail
How does RL verify science data in wet labs?
Latent Space
Why is everyone cloning Deep Research? thumbnail
Why is everyone cloning Deep Research?
Latent Space
How Do Language Agents Reason and Use Tools? thumbnail
How Do Language Agents Reason and Use Tools?
Latent Space