# Hugging Face — 🐯 Liger GRPO meets TRL

- Company: Hugging Face (huggingface.co)
- Announced: 2025-05-25T00:00:00+00:00
- Category: developer-tool-release
- Subject: Platform
- Models affected: Qwen3-0.6B, Qwen3-0.6B-Instruct
- Source: https://huggingface.co/blog/liger-grpo
- Record: https://forck.live/items/1688-liger-grpo-meets-trl

Hugging Face announces the integration of Liger GRPO with TRL, achieving 40% memory reduction in GRPO training with no quality loss, along with FSDP and PEFT support.

## Evidence

Verbatim from https://huggingface.co/blog/liger-grpo:

> Liger supercharges TRL’s Group Relative Policy Optimization (GRPO) Trainer by slashing memory usage by 40% with zero drop in model quality.

---

Record: https://forck.live/items/1688-liger-grpo-meets-trl
Catalogue: https://forck.live/llms.txt
Feed: https://forck.live/feed.md