"Inference Engineering" is now available. Get your copy here

Michael Feil

Model Performance Engineer

Model performance

How we built the fastest Kimi K2.5 on Artificial Analysis

Tri Dao
3 others
kimi k2.5
Model performance

How Baseten achieved 2x faster inference with NVIDIA Dynamo

Abu Qader
2 others
2x faster inference with Nvidia Dynamo
Model performance

Run Qwen3 Embedding on NVIDIA Blackwell GPUs

Michael Feil
1 other
Run Qwen3 Embedding on NVIDIA Blackwell GPUs with Baseten Embeddings Inference (BEI)
AI engineering

Your client code matters: 12x higher embedding throughput with Python and Rust

Michael Feil
The Baseten Performance Client
Model performance

Day zero benchmarks for Qwen 3 with SGLang on Baseten

Yineng Zhang
2 others
Qwen + SGLang
Model performance

How we built BEI: high-throughput embedding, reranker, and classifier inference

Michael Feil
1 other
TensorRT-LLM for embeddings
News

Introducing Baseten Embeddings Inference: The fastest embeddings solution available

Michael Feil
1 other
Introducing BEI

Explore Baseten today

Start deployingTalk to an engineer
Michael Feil - Model Performance Engineer