Hugging Face changelog

Patchwire tracks 2 Hugging Face products for developers: Transformers, huggingface_hub. In the last 30 days we logged 12 releases, most of them from huggingface_hub (10), Transformers (2). The most recent was huggingface_hub: [v2.2.0] `hf jobs stats` snapshots, download and `HfFileSystem` fixes on Oct 8, 2026. Every entry links to the original release notes.

Products

TransformersSDK / library · latest Oct 6, 2026huggingface_hubSDK / library · latest Oct 8, 2026

Thursday, Oct 8

Tuesday, Oct 6

TransformersHugging Face · SDK / library
1 update
Release v5.19.0Copy linkPost on X
Release v5.19.0 New Model additions EmbeddingGemma2 EmbeddingGemma 2 is a multimodal embedding model from Google built on the Gemma 4 architecture. It encodes text, images,…

Thursday, Oct 1

huggingface_hubHugging Face · SDK / library
3 updates
[v2.1.0] Better Jobs tooling, ZeroGPU quota tracking, and revamped Model CatalogCopy linkPost on X
📊 Jobs: retries, rescheduling, and port exposure Hugging Face Jobs get a batch of quality-of-life improvements this release. Jobs can now retry automatically on failure with the…
v2.1.1Copy linkPost on X
[CLI] Rename 'hf spaces zero-gpu-quota' to 'hf spaces zero-gpu quota'- #5055 Full Changelog : v2.1.0...v2.1.1
v2.1.0.rc0Copy linkPost on X
v2.1.0.rc0 pre-release

Wednesday, Sep 30

TransformersHugging Face · SDK / library
1 update
Release 5.18.0Copy linkPost on X
New Model additions Nemotron 3 Diarization Nemotron 3 Diarization is an open-weight streaming speaker diarization model designed to determine "who spoke when" in real-world…

Thursday, Sep 24

huggingface_hubHugging Face · SDK / library
5 updates
[v2.0.0] The httpx2 releaseCopy linkPost on X
See MIGRATION GUIDE in docs. 💔 Breaking Change: HTTP stack moves to httpx2 See migration plan in #4802 . huggingface_hub v2.0 replaces its HTTP dependency with httpx2 : clients…
v2.0.0.rc0Copy linkPost on X
v2.0.0.rc0 pre-release
[v1.33.0] Better UX on large uploads and simpler skills installsCopy linkPost on X
📤 See progress while large Xet uploads validate Very large Xet uploads used to sit silently between "Uploading" and "Committing" while shards were being finalized, which could…
v1.33.0.rc1Copy linkPost on X
v1.33.0.rc1 pre-release
v1.33.0.rc0Copy linkPost on X
v1.33.0.rc0 pre-release

Hugging Face in the news

Embodied Turing Machines Stateful Code for Robot Recursive Self-Improvement paper:@_akhaliq · 8h agoRun fast, private agents on-device with LFM2.5-24B-A2BHugging Face · 8h agoBudgetPix Compute-Adaptive Tokenization for Pixel-Space Image Diffusion paper:@_akhaliq · 1d agoImpactful scheduling for GPU clustersHugging Face · 4d agoThe model that didn t exist, so you made it yourselfHugging Face · 6d agoIntroducing Falcon ASRHugging Face · 7d agoOne Model Family, Two Gold-Level Results: Fine-Tuning Nemotron for IOI and IMOHugging Face · 7d ago
Daily AI dev-tool digestSubscribe