Tricks from OpenAI gpt-oss YOU 🫵 can use with transformers

Hugging Face announces upgrades to the transformers library, including zero-build kernels downloadable from the Hub, MXFP4 quantization, tensor parallelism, expert parallelism, dynamic sliding window layer and cache, continuous batching and paged attention, and faster model loading, inspired by OpenAI's GPT-OSS release. These features are designed to work across major models in transformers.

From the source
To enable the release of gpt-oss through transformers, we have upgraded the library considerably. The updates make it very efficient to load, run, and fine-tune the models.
huggingface.co

Visit source ↗huggingface.co

Announced: 11 Sep 2025 00:00 UTC
Detected: 03 Aug 2026 21:12 UTC (+326d after)

Other stories

Hugging Face · 28 AugThe Open ASR Leaderboard Adds Its First Global South LanguageCapability change

xAI · 29 AugGrok Bot now works with XCapability change

GitHub · 28 AugGitHub Copilot in Visual Studio — August update

GitHub · 28 AugGitHub Copilot weekly releases — August 24Capability change

Amazon · 28 AugBatch write and discover records in Amazon SageMaker Feature Store

API release

Perplexity · 28 AugGLM 5.3API release