Philip Kiely

Lead Developer Advocate

Model performance

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

Pankaj Gupta
2 others
Speculative Decoding with TensorRT-LLM
Model performance

A quick introduction to speculative decoding

Pankaj Gupta
2 others
Intro to Speculative Decoding
Infrastructure

Evaluating NVIDIA H200 Tensor Core GPUs for LLM inference

Pankaj Gupta
1 other
NVIDIA H200
News

Export your model inference metrics to your favorite observability tool

Helen Yang
2 others
Export your inference metrics
Community

Building high-performance compound AI applications with MongoDB Atlas and Baseten

Philip Kiely
MongoDB + Baseten
Model performance

How to build function calling and JSON mode for open-source and fine-tuned LLMs

Bryce Dubayah
1 other
JSON Mode
News

Introducing function calling and structured output for open-source and fine-tuned LLMs

Bryce Dubayah
1 other
Function calling + JSON Mode
AI engineering

The best open-source image generation model

Philip Kiely
Best image generation models
Model performance

How to double tokens per second for Llama 3 with Medusa

Abu Qader
1 other
Double Llama TPS with Medusa
123...7

Explore Baseten today

Start deploying
Talk to an engineer