Hugging Face Programming Tutorials & Engineering Articles

Teams customize their models to hit their targets for latency, speed, memory, and compute. With the open NVIDIA Nemotron family of models…

Alibaba released the open weights for Qwen3.8-2.4T-A95B (Qwen3.8-Max), its largest open-weight model, bringing near-frontier capabilities to the open ecosystem.

Long-running AI agents spend most of their time on high-volume execution: tool calls, result validation, and subagent delegation. Using a frontier reasoning…

Learn how NVIDIA NeMo Switchyard routes AI agent workloads across models using tuning-free and tunable routers that balance model capability, cost, and latency.

Deploying secure, real-time Edge AI on Raspberry Pi is now simplified using LiteRT and lightweight Gemma open models. LiteRT optimizes CPU and GPU performance, delivering fast token speeds for models like Gemma4, enabling real-time local reasoning for robotics. Developers can quickly convert, quantize, and run these models using the lightweight LiteRT CLI tool. Support for Hailo AI accelerators is also coming very soon.

Meta returns to the open source ecosystem with the release of Muse Glimmer, a 30B open-weight dense model with a 120K+ context window built for local AI agentic…

The 2026-07-28 Model Context Protocol (MCP) specification replaces legacy stateful constraints with a fully stateless core, enabling cloud-native horizontal scaling, serverless deployments, and standard round-robin load balancing. This architectural shift introduces standardized HTTP headers for efficient routing without deep packet inspection, caching controls, and Multi Round-Trip Requests (MRTR) to handle interactive and long-running tasks without blocking connections. Developers can immediately begin migrating their agentic applications to this highly scalable infrastructure using the newly available beta SDKs for Python, TypeScript, Go, and C#.

A central challenge in robotics is building policies that generalize beyond the demonstrations they’re trained on. A policy that succeeds in a training scene…

Autonomous vehicle (AV) development often relies on separate models for trajectory generation, high-level intent prediction, scene understanding…

ClickHouse is joining the Open Secure AI Alliance alongside NVIDIA and other industry leaders to help build open tools that keep AI agents secure.

Unlike autonomous driving or industrial robotics, healthcare robotics can’t rely on internet-scale data collection or unlimited real-world experimentation.

NVIDIA Ising Calibration is an open source vision language model (VLM) designed to interpret diagnostic outputs from quantum processors and determine how they…

Modern chip design is increasingly limited by engineering time. Register transfer level (RTL) development and verification require specialized hardware…

Customization is what enables developers to take a general model and tailor it to use cases, domains, languages, and more. However, customization comes with a…

Tunix is Google’s new JAX-native post-training library designed to eliminate TPU idling bottlenecks when training multi-turn, tool-using LLM reasoning agents. It maximizes hardware throughput by combining highly concurrent, asynchronous rollouts with a decoupled producer-consumer pipeline, ensuring the trainer is constantly fed even while agents wait on network I/O or environment steps. Additionally, Tunix provides plug-and-play abstractions and continuous macro-level profiling, allowing developers to easily integrate custom open-source environments and optimize complex distributed workflows without massive code rewrites.

Developers building video analytics applications across large spaces must track the same object as it moves between camera views. Single-camera 2D tracking…

Coding AI agents are becoming practical operators for long-running machine learning (ML) workflows. They can inspect repositories, set up runtimes…

What if autonomous coding AI agents could push your vision reasoning models above 90% accuracy with almost no manual effort? When adapting vision reasoning…

Fine-tuning LLMs for financial natural language processing (NLP) is constrained by limited, imbalanced data. Real-world financial news overrepresents earnings…

We're excited to introduce LiteRT.js, the newest member of the LiteRT family! LiteRT.js is our powerful solution for running machine learning models directly in the browser, extending Google's cross-platform edge AI runtime to the web. Built for JavaScript developers, LiteRT.js delivers state-of-the-art ML model inference performance on WebGPU and upcoming WebNN, with a fallback to WebAssembly for CPU. This post provides a quick tour of LiteRT.js and gives web developers everything they need to get started.

As more teams move from humanoid robot bring-up to task-specific skill development, the need for repeatable development workflows is growing.

Industrial machinery generates more alarms than technicians can triage. For each important alarm requiring follow-up, the technician pulls historical context…

As context windows grow longer, moving large model weights efficiently becomes critical to performance. A common way to address this is quantization…

As AI systems move from single-turn interactions to coordinated multiagent workflows, low-latency inference becomes increasingly important.

Foundation models are reshaping computational biology. Pretrained on massive corpora of protein or genomic sequences, models such as ESM2 (a protein language…

Developers building real-time AI—such as chat assistants, copilots, and agentic workflows—are often constrained by token-by-token generation speed.

As enterprise AI adoption scales, developers are increasingly forced to stitch together fragmented pipelines—separate models for text, vision…

DiffusionGemma is an experimental text-generation model built on the Gemma 4 architecture that uses diffusion-based parallel generation instead of token-by-token autoregression, enabling much faster inference, bidirectional context awareness, and real-time self-correction while remaining deployable on consumer GPUs. Its architecture generates and refines 256-token blocks in parallel through iterative denoising, allowing it to handle complex constraint-based tasks such as Sudoku more effectively than traditional language models and demonstrating strong gains from fine-tuning. The model integrates with vLLM and other popular inference frameworks, giving developers access to a new non-autoregressive approach that combines high performance, efficient long-context scaling, and straightforward customization and deployment.

Single-turn chatbots are evolving into long-running agents that can reason, maintain context, use tools, and run efficiently across many turns to complete…

The newly released Gemma 4 12B is a dense, multimodal model designed for high-performance local AI execution on consumer devices. By introducing a novel, encoder-free architecture, it bypasses traditional visual and audio encoders to feed multimodal data directly into the LLM backbone.

Developing autonomous vehicle (AV) policies requires bridging an important gap between training and deployment. Vision-language-action (VLA) models that can…

Physical AI systems must understand the real world before they can act within it. Robots, autonomous vehicles, and smart spaces need to understand what’s…

AI applications are moving beyond text generation to multimodal systems that can perceive, search, and reason across images, documents, video…

Large language models (LLMs) are revolutionizing the financial trading landscape by enabling sophisticated analysis of vast amounts of unstructured data to…

The Google Tensor ML SDK is graduating to its Beta phase, allowing developers to build and deploy high-performance machine learning models directly onto the TPU of Google Pixel 10 devices. By integrating with LiteRT, Google's edge deployment framework, the SDK provides a unified workflow for developers to convert, compile, and run PyTorch or TFLite models with robust fallback options. Additionally, a new model garden offers over 100 classic and generative AI models, including Gemma 3, enabling low-latency, private features like speech recognition, computer vision, and text generation.

This post is the second of a three-part series. See also Model Quantization: Concepts, Methods, and Why It Matters and Model Quantization: Turn FP8 Checkpoints…

Google Cloud has introduced a high-performance integration that connects Rapid Storage directly to PyTorch via the fsspec interface to eliminate AI training bottlenecks. By utilizing Google’s Colossus architecture and bidirectional gRPC streaming, the solution offers up to 15 TiB/s aggregate throughput and significant reductions in latency. These improvements allow developers to speed up total training time by 23% with zero code changes required beyond updating the storage bucket type.

Agentic systems often reason across screens, documents, audio, video, and text within a single perception‑to‑action loop. However, they still rely on fragmented…

DeepSeek just launched its fourth generation of flagship models with DeepSeek-V4-Pro and DeepSeek-V4-Flash, both targeted at enabling highly efficient million…

LiteRT is a production-ready framework designed to help mobile developers unlock the power of Neural Processing Units (NPUs), overcoming the performance and battery limitations of traditional CPU or GPU processing. By providing a unified API that abstracts away hardware complexities, it allows industry leaders like Google Meet and Epic Games to deploy sophisticated AI models for real-time video, animation, and speech recognition with significantly higher efficiency. The platform further supports developers through benchmarking tools and cross-platform compatibility, enabling seamless AI deployment across mobile devices, AI PCs, and industrial IoT hardware.

MaxText has introduced new support for Supervised Fine-Tuning (SFT) and Reinforcement Learning (RL) on single-host TPU configurations, leveraging JAX and the Tunix library for high-performance model refinement. These features enable developers to easily adapt pre-trained models for specialized tasks and complex reasoning using efficient algorithms like GRPO and GSPO. This update streamlines the post-training workflow, offering a scalable path from single-host setups to larger multi-host configurations.

NVIDIA Ising is the world’s first family of open AI models for building quantum processors, launching with two model domains: Ising Calibration and Ising…

The release of MiniMax M2.7 adds enhancements to the popular MiniMax M2.5 model, built for agentic harnesses, and other complex use cases in fields such as…

In vision AI systems, model throughput continues to improve. The surrounding pipeline stages must keep pace, including decode, preprocessing, and GPU scheduling.

The Gemmaverse expands with the launch of the latest Gemma 4 multimodal and multilingual models, designed to scale across the full spectrum of deployments…

Developing new protein-based therapies and catalysts involves the challenging task of designing protein binders, or proteins that bind to a target protein or…

Agentic AI is an ecosystem where specialized models work together to handle planning, reasoning, retrieval, and safety guardrailing. As these systems scale…

Agentic AI systems need models with the specialized depth to solve dense technical problems autonomously. They must excel at reasoning, coding…

In the rapidly evolving landscape of large language model (LLM) development, NVIDIA Megatron Core has emerged as the foundational framework for training massive…