Blog

Blog

Expert guides and engineering deep dives to help you ship faster, scale easier, and learn along the way.

AllModel performanceAI engineeringInfrastructureNewsCommunity

Announcing Baseten’s $75M Series C

Tuhin Srivastava
Baseten raised a $75M Series C round

How multi-node inference works for massive LLMs like DeepSeek-R1

Phil Howes
1 other
Multi-node inference

Testing Llama 3.3 70B inference performance on NVIDIA GH200 in Lambda Cloud

Pankaj Gupta
1 other
Testing GH200 GPUs

Baseten Chains is now GA for production compound AI systems

Marius Killinger
2 others
Baseten Chains

Private, secure DeepSeek-R1 in production in US & EU data centers

Amir Haghighat
1 other
DeepSeek R1

Driving model performance optimization: 2024 highlights

Pankaj Gupta
MP 2024 highlights

New observability features: activity logging, LLM metrics, and metrics dashboard customization

Suren Atoyan
4 others
Observability

How we built production-ready speculative decoding with TensorRT-LLM

Pankaj Gupta
2 others
Speculative Decoding with TensorRT-LLM

A quick introduction to speculative decoding

Pankaj Gupta
2 others
Intro to Speculative Decoding
123...12