TRL v1.15 is out, and it’s an absolute banger of a release for memory-efficient post-training. The main change: SFT, DPO, KTO, GRPO, RLOO an…

TRL v1.15 is out, and it’s an absolute banger of a release for memory-efficient post-training. The main change: SFT, DPO, KTO, GRPO, RLOO and Distillation now use a fused LM head by default. Instead of materializing the huge [batch, seq, vocab] logits tensor, a Triton kernel computes the token-level quantities we actually need directly. The results are significant 👇 On Gemma 3 1B with a 262k vocabulary, on the same GPU: DPO: 10k → 59k max sequence length KTO: 9k → 63k GRPO: 28k → 114k RLOO: 23k → 100k SFT: 20k → 107k Up to 6.9x longer sequences, with peak memory at 8k context reduced by 52-82%. Speed is not negatively impacted: training is up to ~11% faster. Nothing to enable: this is now the default in TRL v1.15! There’s more in the release too: selective activation checkpointing for SFT, assistant-only loss for vision datasets, better conversation logging, improvements to AsyncGRPO / AsyncDistillation, and a long list of fixes. I really like optimizations like this: the training API doesn’t need to become more complicated as the implementation underneath gets much better. https://github.com/huggingface/trl/releases/tag/v1.15.0

Related

• Introducing ml-intern, the agent that just automated the post-training team @huggingface It's an open-source implementation of the real rese…
• ml-intern by @huggingface is wild 🔥 You drop a high-level prompt (“build the best scientific reasoning model” or “crush healthcare benchmar…
• HUGGING FACE JUST AUTOMATED THEIR ENTIRE POST-TRAINING TEAM WITH AN AGENT. It reads papers, runs GPU experiments, iterates, and builds resea…
• Hugging Face Releases ml-intern: An Open-Source AI Agent that Automates the LLM Post-Training Workflow [The 'AI Intern' that actually ships …

Source: Clem Delangue (X) | 2026-10-09