55 blog posts published by month since the start of 2024. Start from a different year:

Posts year-to-date
18 (37 posts by this month last year.)
Average posts per month since 2024
2.3

Post details (2024 to today)

Title Author Date Word count HN points
Product Updates - February 2024 Will Van Eaton and Abhay Malik Feb 13, 2024 338 -
15x Faster Fine-Tuning in Under 15 Days Arnav Garg Jul 02, 2024 1867 -
The First Reinforcement Fine-Tuning Platform for LLMs Devvret Rishi and Travis Addair Mar 19, 2025 1316 -
Not Your Average VPC: Secure AI in Your Private Cloud with Direct Ingress Noah Yoshida and Michael Ortega Aug 13, 2025 1028 -
Fine-Tuned: January 2024 Predibase Team Jan 28, 2024 897 -
2023 December Newsletter Predibase Team Jan 17, 2024 1033 -
How to Fine-tune And Serve VLMs in Predibase Timothy Wang Jan 07, 2025 1359 -
12 Best Practices for Distilling Small LMs from GPT Justin Zhao and Wael Abid Jan 16, 2024 5092 -
Try 10x Faster Fine-Tuning Abhay Malik Apr 25, 2024 616 -
Real-World LLM Inference Benchmarks: How Predibase Built the Fastest Stack Chloe Leung May 28, 2025 1683 -
How DeepSeek-R1 Beats o1 with Reinforcement Learning Will Van Eaton Jan 29, 2025 1410 -
The 5 Hidden Hurdles of Building AI Infra Michael Ortega Jul 02, 2025 1065 -
Predibase will be joining forces with Rubrik Devvret Rishi Jun 25, 2025 1488 -
Turbo LoRA: 2-3x faster fine-tuned LLM inference Travis Addair and Arnav Garg Aug 02, 2024 3618 -
Train AI to Write GPU Code via Reinforcement Fine-Tuning Arnav Garg, Travis Addair and Will Van Eaton Feb 14, 2025 2055 -
How to Fine-Tune Zephyr-7B for Support Call Analysis Alex Sherstinsky and Magdy Saleh Jan 08, 2024 2719 -
Improving Agent Feedback with Multi-LoRA at Convirza Will Van Eaton Nov 25, 2024 974 -
Fine-Tuned Newsletter: April-May 2024 Will Van Eaton May 21, 2024 551 -
Guide to Reward Functions in Reinforcement Fine-Tuning Joppe Geluykens Apr 09, 2025 2524 -
DeepSeek Survey Results: Insights from AI Leaders Will Van Eaton Apr 16, 2025 456 -
Product Updates - September 2024 Will Van Eaton Sep 18, 2024 860 -
How Upstage Built a Highly Accurate SLM for Proofreading Devvret Rishi and Kasey Roh Sep 09, 2024 904 -
How to Deploy LLaMA 4 Models in Your VPC or Cloud Martin Davis and Michael Ortega Apr 14, 2025 1647 -
Fine-Tuned Newsletter: June 2024 Will Van Eaton Jul 02, 2024 774 -
Manage Your LLM Deployments with Command Center Will Van Eaton Mar 29, 2024 661 -
How to Deploy and Serve Qwen 3 in Your Private Cloud (VPC) Michael Ortega and Magdy Saleh May 01, 2025 2339 -
Why Reinforcement Learning Beats SFT with Limited Data Travis Addair and Arnav Garg Feb 11, 2025 2995 -
Introducing the Fine-Tuning Index for LLMs Will Van Eaton May 21, 2024 382 -
5 Reasons Why LoRA Adapters are the Future of Fine-tuning Predibase Team Jun 10, 2024 2493 -
How to Efficiently Fine-Tune CodeLlama-70B Instruct Alex Sherstinsky Feb 08, 2024 2247 -
AI and LLM Predictions for 2024 Michael Ortega Jan 29, 2024 2178 -
Fine-Tuned: February-March 2024 Predibase Team Mar 04, 2024 939 -
Apple’s GenAI Architecture: Small, Fine-Tuned & LoRA-Based Devvret Rishi Jun 13, 2024 713 -
LoRAX + Outlines: Better JSON Extraction with LoRA Jeffrey Tang and Travis Addair Mar 03, 2024 2285 -
Optimize LLM Performance with Deployment Health Analytics Will Van Eaton Sep 11, 2024 971 -
Training an Expert Coding Agent with Reinforcement Fine-Tuning Evan Sandler, Ross Favero and Ajinkya Tejankar May 20, 2025 2561 -
LLM Serving Guide: How to Build Faster Inference for Open-source Models Michael Ortega May 12, 2025 1794 -
Predibase Wrapped: Our greatest hits of 2024 Will Van Eaton Dec 19, 2024 1622 -
Build an SQL Copilot with LLMs and Synthetic Data Alex Sherstinsky and Yev Meyer Jul 11, 2024 2434 -
Fine-Tuned SLMs Help Checkr Optimize Background Checks Vlad Bukhin, Staff ML Engineer at Checkr Oct 03, 2024 1863 -
The First Serverless Solution for Fine-Tuned LLMs Abhay Malik Feb 13, 2024 830 -
Next-Gen Inference Engine for Fine-Tuned SLMs Will Van Eaton Oct 15, 2024 2475 -
Fine-Tuned Newsletter: March 2024 Predibase Team Mar 31, 2024 688 -
Personalizing Trading with Deep Learning on Snowflake Joppe Geluykens and Michael Ortega Jan 20, 2024 1395 -
Self-Distilling DeepSeek-R1 with Turbo Speculation - 2x Inference Ajinkya Tejankar and Will Van Eaton Feb 19, 2025 1887 -
Build an SLM That Outperforms GPT-4o with Synthetic Data Chloe Leung Oct 30, 2024 2900 -
LoRA Land: Open-Source LLMs That Beat GPT-4 Timothy Wang, Justin Zhao and Will Van Eaton Feb 20, 2024 1821 -
How to Efficiently Fine-Tune Gemma-7B with Open-Source Ludwig Alex Sherstinsky Feb 23, 2024 787 -
7 Things to Know About Fine-Tuning LLMs Geoffrey Angus Feb 22, 2024 3475 -
DeepSeek Deployment Guide for VPC and SaaS Clouds Will Van Eaton Jan 31, 2025 1505 -
Solar LLM: Fine-Tuned Performance That Beats GPT-4 Arnav Garg, Junyeop Lee, Lucy Park, Kasey Roh and Will Van Eaton Jun 17, 2024 1142 -
Agentic AI at Scale: Marsh McLennan Saves 1M+ Hours Will Van Eaton Mar 12, 2025 1042 -
Product Updates - March 2024 Will Van Eaton Mar 29, 2024 459 -
How to Fine-Tune LLaMA 3 for Customer Support Tasks Chloe Leung Apr 30, 2024 1925 -
Ludwig 10k Stars LLM Fine-tuning Hackathon Winners Alex Sherstinsky and Michael Ortega Feb 01, 2024 1297 -