Baseten

Engineering blog · baseten.co/blog

Watch

196posts0this week0watchers

WatchOpen blog (opens in a new tab)

BasetenBlog2w

NVIDIA Nemotron 3 Diarization: real-time speaker labels at a cent per audio hour

BasetenBlog3w

Introducing Baseten Hosted Tools

BasetenBlog3w

LangChain trains custom models for LangSmith Engine with Baseten Loops

BasetenBlog4w

DeepSeek-V4.1-Flash: more efficient prefill for coding agents

BasetenBlog4w

Blaxel is joining Baseten to build the future of agentic infrastructure

BasetenBlog4w

How Baseten makes pyannote’s diarization models 9.6x faster

BasetenBlog4w

Optimizing delta weight syncs for managed rollouts

BasetenBlog4w

Baseten leads Coval’s voice AI benchmark

BasetenBlog2 Sept

New MCP and skill for coding agents to use Baseten

BasetenBlog2 Sept

Best open-source models for post-training

BasetenBlog2 Sept

The efficient frontier of LLM inference

BasetenBlog29 Aug

Agentic kernels in production

BasetenBlog28 Aug

GLM 5.3: Scaling with post-training, intuitively explained

BasetenBlog25 Aug

The two AI gateway patterns in production inference

BasetenBlog25 Aug

How to run any open model inside DeepSeek Harness

BasetenBlog24 Aug

How leading platforms ensure observability for LLM inference

BasetenBlog14 Aug

Inference engineering for DeepSeek V4 Pro 0813

BasetenBlog11 Aug

Introducing NVIDIA Nemotron 3.5 Lightning

BasetenBlog4 Aug

Introducing NVIDIA Nemotron 3.5 ASR Streaming

BasetenBlog3 Aug

Laguna S 2.1 goes Greek: a repository-scale game transformation

Showing the newest 48 of 196 posts. Browse by feature trail