Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality IA Granite Embedding Multilingual R2: Open Apache 2.0 Multilingual Embeddings with 32K Context — Best Sub-100M Retrieval Quality 14 mai 2026 Hugging Face Lire
Unlocking asynchronicity in continuous batching IA Unlocking asynchronicity in continuous batching 14 mai 2026 Hugging Face Lire
Building Blocks for Foundation Model Training and Inference on AWS IA Building Blocks for Foundation Model Training and Inference on AWS 11 mai 2026 Hugging Face Lire
MachinaCheck: Building a Multi-Agent CNC Manufacturability System on AMD MI300X IA MachinaCheck: Building a Multi-Agent CNC Manufacturability System on AMD MI300X 10 mai 2026 Hugging Face Lire
"OncoAgent: A Dual-Tier Multi-Agent Framework for Privacy-Preserving Oncology Clinical Decision Support" IA "OncoAgent: A Dual-Tier Multi-Agent Framework for Privacy-Preserving Oncology Clinical Decision Support" 9 mai 2026 Hugging Face Lire
CyberSecQwen-4B: Why Defensive Cyber Needs Small, Specialized, Locally-Runnable Models IA CyberSecQwen-4B: Why Defensive Cyber Needs Small, Specialized, Locally-Runnable Models 8 mai 2026 Hugging Face Lire
EMO: Pretraining mixture of experts for emergent modularity IA EMO: Pretraining mixture of experts for emergent modularity 8 mai 2026 Hugging Face Lire
vLLM V0 to V1: Correctness Before Corrections in RL IA vLLM V0 to V1: Correctness Before Corrections in RL 6 mai 2026 Hugging Face Lire
Adding Benchmaxxer Repellant to the Open ASR Leaderboard IA Adding Benchmaxxer Repellant to the Open ASR Leaderboard 6 mai 2026 Hugging Face Lire
AI evals are becoming the new compute bottleneck IA AI evals are becoming the new compute bottleneck 29 avril 2026 Hugging Face Lire
Granite 4.1 LLMs: How They’re Built IA Granite 4.1 LLMs: How They’re Built 29 avril 2026 Hugging Face Lire
DeepInfra on Hugging Face Inference Providers 🔥 IA DeepInfra on Hugging Face Inference Providers 🔥 29 avril 2026 Hugging Face Lire
Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents IA Introducing NVIDIA Nemotron 3 Nano Omni: Long-Context Multimodal Intelligence for Documents, Audio and Video Agents 28 avril 2026 Hugging Face Lire
How to build scalable web apps with OpenAI's Privacy Filter IA How to build scalable web apps with OpenAI's Privacy Filter 27 avril 2026 Hugging Face Lire
DeepSeek-V4: a million-token context that agents can actually use IA DeepSeek-V4: a million-token context that agents can actually use 24 avril 2026 Hugging Face Lire
