# TRL v1.0 — Hugging Face Post-Training Library Reaches Stable

> The go-to library for aligning LLMs hits 1.0 with stable APIs and 75+ post-training methods.

- Org: Hugging Face
- Date: 2026-03-31
- Category: tool, repo
- Source: https://huggingface.co/blog/trl-v1
- Canonical page: https://ai-tldr.dev/releases/huggingface-trl-v1/

## In short

First stable release of the dominant LLM post-training library. Ships 75+ alignment methods (SFT, DPO, GRPO, KTO), weekly releases, Unsloth integration for 2x training speed, and 3M monthly PyPI downloads.

## What it is

TRL (Transformer Reinforcement Learning) is Hugging Face's library for post-training language models. The v1.0 release marks the transition from research-oriented tool to production-ready framework with stable APIs, semantic versioning, and a clear separation between stable and experimental methods.

## How it works

TRL provides trainers for supervised fine-tuning (SFT), reward modeling, and multiple alignment algorithms including DPO, GRPO, RLOO, and KTO. It integrates with Accelerate for multi-GPU/multi-node scaling and with Unsloth for up to 2x training speedup and 70% memory reduction. Starting with v1.0, minor releases ship weekly so new model support lands fast.

## Why it matters

Post-training is the step that turns a pretrained model into something useful for a specific task. TRL 1.0 makes this step reliable enough for production workflows, with stable APIs that teams can build CI/CD pipelines around. At 3M monthly downloads, it is the dominant library in this space.

## Who it's for

ML engineers fine-tuning or aligning LLMs.

## Try it

pip install --upgrade trl

## Links

- [Announcement](https://huggingface.co/blog/trl-v1)
- [Repo](https://github.com/huggingface/trl)
- [Docs](https://huggingface.co/docs/trl)