|
22,580: GPT-2 to Kimi K3, explained
|
Ali Taha |
2026-07-30 |
4,626 |
--
|
|
How to run Kimi K3 in any harness: routing with Baseten Switch
|
Zak Keener, Alex Ker |
2026-07-30 |
881 |
--
|
|
Announcing Baseten for Model Labs
|
Marylise Tauzia, Bola Malek |
2026-07-29 |
1,251 |
--
|
|
Welcome, Mani Parkhe!
|
Colin McGrath, Sameer Paranjpye, Amir Haghighat |
2026-07-28 |
273 |
--
|
|
Making Kimi K3 tokenization 18x faster for million-token agentic workloads
|
Michael Feil |
2026-07-27 |
1,289 |
--
|
|
How to build a day-0 API for Kimi K3
|
Model Performance Team |
2026-07-27 |
1,885 |
2
|
|
How we built the new fastest API for GLM-5.2
|
Alex Korte, Magdy Saleh, Tri Dao, Anant Desai, Bryce Dubayah, Abu Qader, Philip Kiely |
2026-07-26 |
524 |
2
|
|
Introducing GLM 5.2 Fast
|
Abu Qader, Philip Kiely, Alina Weinstein |
2026-07-23 |
387 |
--
|
|
How to optimize LLM inference speed and reduce costs in production
|
Chloe Florit |
2026-07-23 |
2,085 |
--
|
|
How to choose an AI model: lessons from Notion and Gamma
|
Chloe Florit |
2026-07-23 |
1,211 |
--
|
|
H100 vs. H200 GPUs
|
Chloe Florit |
2026-07-22 |
1,019 |
--
|
|
GLM 5.2 With Vision
|
Harry Partridge |
2026-07-22 |
812 |
--
|
|
Real-time video generation inference on Baseten
|
Ali Taha, Brendan Duke, Yikai Zhu, Faraz Shahsavan, Pankaj Gupta, Philip Kiely |
2026-07-16 |
1,287 |
--
|
|
Fast, accurate retrieval with NVIDIA Nemotron 3 Embed
|
Albert Lee |
2026-07-16 |
963 |
--
|
|
Meet Inkling: Thinking Machines Lab's new customizable model
|
Albert Lee |
2026-07-15 |
736 |
--
|
|
Introducing Step 3.7 Flash: multimodal reasoning at scale
|
Albert Lee |
2026-07-14 |
631 |
--
|
|
Building with NVIDIA Nemotron 3 Ultra and LangChain Deep Agents Code on Baseten
|
Philip Kiely |
2026-07-08 |
900 |
--
|
|
H100 vs. H200 vs. B200: which GPU should you use?
|
Chloe Florit |
2026-07-02 |
1,282 |
--
|
|
AI training vs. inference: what's the difference?
|
Mahmoud Hassan |
2026-06-26 |
1,806 |
--
|
|
How to run GLM-5.2 in any harness
|
Archit Mishra 2 others |
2026-06-26 |
364 |
--
|
|
Live draft model training for speculative decoding
|
Chloe Florit |
2026-06-25 |
808 |
--
|
|
NVIDIA BioNeMo Agent Toolkit on Baseten
|
Chloe Florit |
2026-06-24 |
1,269 |
--
|
|
How we built the world’s fastest API for GLM-5.2
|
Yikai Zhu 2 others |
2026-06-23 |
1,445 |
3
|
|
Announcing our Series F
|
Dannie Herzberg 1 other |
2026-06-23 |
381 |
5
|
|
The best open-source large language models (LLMs)
|
Kumar Chellapilla 4 others |
2026-06-18 |
1,769 |
--
|
|
Rolling deployments for zero-downtime model updates
|
Ian Carrasco 1 other |
2026-06-12 |
900 |
--
|
|
Mercury 2, the first reasoning diffusion LLM, is now on Baseten
|
Fred Liu |
2026-06-12 |
1,255 |
--
|
|
Introducing NVIDIA Nemotron 3 Ultra: The Nemotron 3.x family is here!
|
Marylise Tauzia |
2026-06-05 |
1,638 |
--
|
|
Welcome, Gabe Stern!
|
Amir Haghighat |
2026-06-05 |
201 |
--
|
|
MAI-Thinking-1 is coming to Baseten
|
Fred Liu |
2026-06-02 |
728 |
--
|
|
Nvidia Cosmos 3: Robots finally take over
|
Madison Kanna |
2026-06-01 |
1,462 |
--
|
|
Timestep distillation: 2.5x faster FLUX.2 image generation
|
Faraz Shahsavan 3 others |
2026-05-29 |
1,797 |
--
|
|
Powering Inference for the Continual Learning Era
|
Madison Kanna |
2026-05-28 |
1,407 |
--
|
|
The beginner’s guide to open-source AI models
|
Madison Kanna |
2026-05-28 |
1,490 |
--
|
|
Sub-second image generation with Flux.2 and Qwen-Image
|
Aaryam Sharma |
2026-05-18 |
750 |
--
|
|
Cost-efficient, high-performance TTS with Qwen3-TTS
|
Alex Ker 1 other |
2026-05-15 |
1,781 |
--
|
|
DFlash: 3x faster LLM inference
|
Model Performance Team |
2026-05-08 |
1,345 |
--
|
|
Introducing the Baseten Loops SDK
|
Bola Malek 1 other |
2026-05-08 |
734 |
--
|
|
Introducing the Baseten Frontier Gateway
|
Raymond Cano |
2026-05-07 |
1,160 |
--
|
|
NVIDIA Nemotron 3 Nano Omni: Build multimodal agents on Baseten
|
Rachel Rapp |
2026-04-29 |
685 |
--
|
|
How we built RBAC that scales for the enterprise
|
Gregory Kofman 2 others |
2026-04-23 |
1,740 |
--
|
|
Harnesses are everything. Here's how to optimize yours.
|
Alex Ker |
2026-04-18 |
1,747 |
--
|
|
How to train custom EAGLE-3 heads for speculative decoding
|
Michael Feil 1 other |
2026-04-14 |
1,396 |
--
|
|
How the Baseten Delivery Network (BDN) makes cold starts fast
|
Gregory Kofman 2 others |
2026-04-10 |
1,801 |
--
|
|
Sub-3 millisecond named entity recognition (NER) inference
|
Michael Feil 1 other |
2026-04-07 |
1,572 |
--
|
|
Open-source LLM training is a mess. Here is how it all works.
|
Paras Stefanopoulos |
2026-04-01 |
3,472 |
--
|
|
Baseten Training: an autoresearch substrate
|
Raymond Cano |
2026-04-01 |
1,108 |
--
|
|
I spent 31 hours on the math behind TurboQuant so you don't have to
|
Ali Taha |
2026-03-27 |
3,489 |
8
|
|
Welcome Sameer Paranjpye!
|
Amir Haghighat |
2026-03-25 |
171 |
--
|
|
Introducing the Baseten Delivery Network: Fast cold starts for big models
|
Stephen Day 3 others |
2026-03-20 |
1,521 |
--
|
