llama

Multi-Region training with Amazon SageMaker HyperPod and QumuloSep 24, 2026 · PolicyChange → Accelerating vision-language models with LFM2.5-VL-DSparkSep 24, 2026 · HardwareLaunch → Accelerate multimodal RL training with SkyRL on Amazon SageMaker HyperPodSep 22, 2026 · OpenSourceRelease → How Cloudflare addressed a cross-tenant data exposure vulnerability in ContainersSep 22, 2026 · SecurityIncident → v0.30.0Sep 22, 2026 · ModelRelease → Transformers now runs llama.cpp quantsSep 22, 2026 · OpenSourceRelease → Pruning LLMs Like a Physicist: Block Removal as an Ising Optimization ProblemSep 21, 2026 · Other → tokenizers v1: encode, decode and scaling, measuredSep 21, 2026 · ProductUpdate → v0.34.3Sep 19, 2026 · ProductUpdate → Python Workers are now generally availableSep 18, 2026 · ProductUpdate → v0.34.2Sep 15, 2026 · ProductUpdate → When scanners miss the attack: how Cloudflare Client-Side Security protects storefrontsSep 15, 2026 · Acquisition → v0.34.1Sep 14, 2026 · ModelRelease → Release 5.17.0Sep 9, 2026 · HardwareLaunch → v0.34.0Sep 5, 2026 · ProductUpdate → Fine-tuning a 350M Model for Better Structured Outputs in 100 GRPO StepsSep 3, 2026 · PolicyChange → v0.33.3Sep 2, 2026 · ProductUpdate → Introducing context-aware vulnerability discovery and remediation with Cloudflare Managed Defense and OpenAI Daybreak modelsSep 1, 2026 · SecurityIncident → Introducing Adaptive Intelligence: Undermining the economics of every bot attackAug 28, 2026 · OpenSourceRelease → v0.33.1Aug 26, 2026 · ProductUpdate → Release v5.16.1Aug 26, 2026 · ProductUpdate → Release: v5.16.0Aug 26, 2026 · ModelRelease → Granite 4.2 LLMs: How They're BuiltAug 25, 2026 · Acquisition → How we saved 100 terabytes of memory by optimizing 1.1.1.1’s DNS cacheAug 24, 2026 · ProductLaunch → v0.33.0Aug 21, 2026 · ProductLaunch → Up to 3.2x Faster Inference with LFM2.5-DSparkAug 20, 2026 · HardwareLaunch → v0.32.15Aug 19, 2026 · ProductLaunch → langchain-openai==1.5.2a1Aug 18, 2026 · SecurityIncident → v0.32.14Aug 14, 2026 · ProductUpdate → v0.32.12Aug 14, 2026 · Other → v0.32.11Aug 14, 2026 · ApiUpdate → Record, train, and deploy from one place with Strands Agents, LeRobot, and Hugging Face Storage BucketsAug 13, 2026 · OpenSourceRelease → v0.32.9Aug 11, 2026 · ProductUpdate → v0.32.8Aug 10, 2026 · ProductLaunch → Release: v5.15.0Aug 10, 2026 · SecurityIncident → Making Knowledge Distillation Cheap Enough to Run at ScaleAug 10, 2026 · OpenSourceRelease → Meta is back with Muse Glimmer: local, agentic, multimodal, and open sourceAug 10, 2026 · Research → dotnet-1.79.0Aug 6, 2026 · SecurityIncident → v0.32.6Aug 4, 2026 · ProductUpdate → v0.32.5Jul 27, 2026 · ProductUpdate → v0.32.4Jul 23, 2026 · ProductUpdate → v0.32.1Jul 16, 2026 · ProductLaunch → Welcome Inkling by Thinking MachinesJul 15, 2026 · PolicyChange → v0.32.0Jul 11, 2026 · ProductLaunch → Native-speed vLLM transformers modeling backendJul 7, 2026 · ModelRelease → v0.31.2Jul 6, 2026 · ProductLaunch → PRX Part 4: Our Data StrategyJul 6, 2026 · Other → Release v5.13.0Jul 3, 2026 · ModelRelease → v0.31.1Jun 30, 2026 · ProductUpdate → Featuring Every Eval Ever Results on Hugging Face Model PagesJun 30, 2026 · Research → v0.24.0Jun 29, 2026 · SecurityIncident → Run a vLLM Server on HF Jobs in One CommandJun 26, 2026 · ProductLaunch → v0.30.11Jun 25, 2026 · ProductLaunch → Experimenting with the proposed Cross-Origin Storage API in Transformers.jsJun 23, 2026 · OpenSourceRelease → Beyond LoRA: Can you beat the most popular fine-tuning technique?Jun 18, 2026 · Partnership → v0.30.10Jun 17, 2026 · ProductUpdate → v0.30.9Jun 15, 2026 · ProductLaunch → v0.23.0Jun 15, 2026 · Funding → v0.30.8Jun 12, 2026 · ProductLaunch → v0.30.7Jun 7, 2026 · ProductLaunch → Nemotron 3.5 Content Safety: Customizable Multimodal Safety for Global Enterprise AIJun 4, 2026 · PolicyChange → v0.30.6Jun 3, 2026 · ModelRelease → v0.30.2Jun 3, 2026 · ProductLaunch → Reachy Mini goes fully localMay 25, 2026 · Funding → Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval QualityMay 14, 2026 · Research → v0.24.0May 14, 2026 · ProductLaunch → PyTorch 2.12.0 ReleaseMay 13, 2026 · HardwareLaunch → v0.30.0May 12, 2026 · ProductUpdate → v0.23.2May 7, 2026 · ProductLaunch → v0.23.1May 5, 2026 · ProductUpdate → Release 5.8.0May 5, 2026 · Funding → v0.23.0May 3, 2026 · ProductLaunch → v0.22.1Apr 28, 2026 · ProductLaunch → v0.22.0Apr 28, 2026 · ModelRelease → v0.21.3Apr 24, 2026 · ProductUpdate → v0.21.2Apr 23, 2026 · ProductLaunch → QIMMA قِمّة ⛰: A Quality-First Arabic LLM LeaderboardApr 21, 2026 · Research → Ecom-RLVE: Adaptive Verifiable Environments for E-Commerce Conversational AgentsApr 16, 2026 · Research → The PR you would have opened yourselfApr 15, 2026 · ProductUpdate → Multimodal Embedding & Reranker Models with Sentence TransformersApr 9, 2026 · ProductUpdate → Welcome Gemma 4: Frontier multimodal intelligence on deviceApr 2, 2026 · ProductUpdate → TRL v1.0: Post-Training Library Built to Move with the FieldMar 31, 2026 · PolicyChange → Release v5.4.0: PaddlePaddle models 🙌, Mistral 4, PI0, VidEoMT, UVDoc, SLANeXt, Jina Embeddings v3Mar 27, 2026 · ModelRelease → Liberate your OpenClawMar 27, 2026 · ProductUpdate → Build a Domain-Specific Embedding Model in Under a DayMar 20, 2026 · ProductUpdate → State of Open Source on Hugging Face: Spring 2026Mar 17, 2026 · Acquisition → Ulysses Sequence Parallelism: Training with Million-Token ContextsMar 9, 2026 · Research → v0.17.0Mar 7, 2026 · Partnership → v5.3.0: EuroBERT, VibeVoice ASR, TimesFM2.5, PP-DocLayoutV2, OlmoHybrid, ModernVBert, Higgs Audio V2Mar 4, 2026 · SecurityIncident → GGML and llama.cpp join HF to ensure the long-term progress of Local AIFeb 20, 2026 · Acquisition → vectordata-dotnet-10.0.0Feb 18, 2026 · ProductUpdate → v5.2.0: GLM-5, Qwen3.5, Voxtral Realtime, VibeVoice Acoustic TokenizerFeb 16, 2026 · HardwareLaunch → Introducing SyGra StudioFeb 5, 2026 · ProductLaunch → v5.1.0: EXAONE-MoE, PP-DocLayoutV3, Youtu-LLM, GLM-OCRFeb 5, 2026 · ModelRelease → v0.15.1Feb 4, 2026 · SecurityIncident → The Future of the Global Open-Source AI Ecosystem: From DeepSeek to AI+Feb 3, 2026 · Funding → We Got Claude to Build CUDA Kernels and teach open models!Jan 28, 2026 · ProductUpdate → Alyah ⭐️: Toward Robust Evaluation of Emirati Dialect Capabilities in Arabic LLMsJan 27, 2026 · Acquisition → Transformers v5Jan 26, 2026 · ProductLaunch → AssetOpsBench: Bridging the Gap Between AI Agent Benchmarks and Industrial RealityJan 21, 2026 · Research →