# Hugging Face TRL Fix Halves Qwen3 Training Step

> Hugging Face's TRL fix cuts Qwen3 training time on H100 by half in SDPA test.
- Title: Hugging Face TRL Fix Halves Qwen3 Training Step · RuntimeWire
- Summary: Hugging Face's TRL fix cuts Qwen3 training time on H100 by half in SDPA test. Hugging Face merged a TRL fix on November 13th, 2026 that halves Qwen3 training…
- Keywords: hugging face, trl, qwen3, h100, sdpa, trainium2, RuntimeWire
- Source: RuntimeWire — https://runtimewire.com/article/hugging-face-trl-packed-batches-rows-h100-trainium
- Author: RuntimeWire
- Published: 2026-11-14T05:41:34.553+00:00
- Read time: 1 min
- Topics: hugging face, trl, qwen3, h100, sdpa, trainium2, technology, ai
## Hugging Face TRL Fix
Hugging Face merged a TRL fix on November 13th, 2026 that halves a reported Qwen3 training step on an H100.
## AWS Trainium2 Test
The fix produced step timings on AWS Trainium2 where the previous layout crashed.
## Packed Examples
The merged pull request keeps best-fit-decreasing packed examples as separate batch rows for standard attention models.
## Key takeaway

Hugging Face merged a TRL fix on November 13th, 2026 that halves Qwen3 training steps on H100 using AWS Trainium2.