Hugging Face Blog the engineering blog of Hugging Face: latest posts and feed

Hugging Face · Engineering blog · 20 a month · last post Sep 23, 2026 · Active

Posts

Latest 200 of 867 on file

200 of 200 posts

Date	Post	Topic	When
Sep 23	How to Use NVIDIA Warp and MjWarp to Accelerate Robotics Simulation and Learning Workflows Sep 23 · Product and company	Product and company	yesterday
Sep 22	Jun Kim, oMLX creator and maintainer, joins Hugging Face to support the MLX community Sep 22 · Databases	Databases	2d ago
Sep 22	Transformers now runs llama.cpp quants Sep 22 · Machine learning	Machine learning	2d ago
Sep 22	How UK AISI and EvalEval Are Making Benchmark Results Reproducible Sep 22 · Reliability and performance	Reliability and performance	2d ago
Sep 21	tokenizers v1: encode, decode and scaling, measured Sep 21 · Reliability and performance	Reliability and performance	3d ago
Sep 21	Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization Problem Sep 21 · AI and agents	AI and agents	3d ago
Sep 15	Your Agent Aced the Task. Will It Do It Again? Sep 15 · AI and agents	AI and agents	9d ago
Sep 10	Rebuilding AUTOMATIC1111 with Gradio Workflow Sep 10 · Product and company	Product and company	2w ago
Sep 10	Async GRPO with LoRA across HF Jobs: a bucket, a proxy, and no NCCL Sep 10 · Product and company	Product and company	2w ago
Sep 3	Training a coding model to paint watercolours with TRL and OpenEnv Sep 3 · Machine learning	Machine learning	3w ago
Sep 3	Give Your Coding Agents a Memory You Own Sep 3 · AI and agents	AI and agents	3w ago
Sep 3	Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO Steps Sep 3 · AI and agents	AI and agents	3w ago
Sep 3	NeoMME: an efficient Multimodal-native and Multilingual Encoder Sep 3 · Product and company	Product and company	3w ago
Sep 1	Introducing @huggingface/kernels: 200+ WebGPU Kernels for Local AI Sep 1 · Product and company	Product and company	3w ago
Sep 1	BenchMIRT: What are LLM benchmarks actually measuring? Sep 1 · AI and agents	AI and agents	3w ago
Aug 28	The Open ASR Leaderboard Adds Its First Global South Language Aug 28 · Product and company	Product and company	4w ago
Aug 26	Training and Finetuning Multi-Vector Embedding Models with Sentence Transformers Aug 26 · AI and agents	AI and agents	4w ago
Aug 25	Wire It, Run It, Deploy It: AI Workflows in Gradio Aug 25 · Product and company	Product and company	4w ago
Aug 25	Quantization-Aware Healing: a compressed, 4-bit model that outperforms its full-precision original Aug 25 · Product and company	Product and company	4w ago
Aug 25	Granite 4.2 LLMs: How They're Built Aug 25 · AI and agents	AI and agents	4w ago
Aug 21	Measuring benchmark optimization in speech recognition Aug 21 · Reliability and performance	Reliability and performance	5w ago
Aug 21	How Hugging Face Inference Endpoints, Jobs, and Buckets Power Search on Papers with Code Aug 21 · AI and agents	AI and agents	5w ago
Aug 20	Up to 3.2x Faster Inference with LFM2.5-DSpark Aug 20 · AI and agents	AI and agents	5w ago
Aug 18	Multi-Vector (Late Interaction) Embedding Models with Sentence Transformers Aug 18 · AI and agents	AI and agents	5w ago
Aug 18	How Much Memory Does Your Agent Actually Need? Aug 18 · AI and agents	AI and agents	5w ago

About this blog

Open models, datasets, transformers, fine-tuning and inference.

Feed

https://huggingface.co/blog/feed.xml

Posts per week, last 26 weeks

20 a month over the last six months (or since the feed's oldest post)

Posts by month

Writes about

AI and agents (44), Product and company (43), Machine learning (15) in the last six months.

Hugging Face

Hugging Face on Companies (companies.fru.dev)

Across fru.dev:Acquisitions·Changefeed

History

Listed on Blogs Sep 24, 2026. No changes to its feed, status or cadence since.

Titles, dates and short excerpts from each blog’s own public feed; every post belongs to its company and links to the original. Logos via logo.dev; trademarks belong to their owners.